]> Phoenix R&D

ietf@raphaelrobert.com

Security Messaging Layer Security messaging layer security end-to-end encryption application api extension extensibility The Messaging Layer Security (MLS) protocol is an asynchronous group authenticated key exchange protocol. MLS provides a number of capabilities to applications, as well as several extension points internal to the protocol. This document provides a consolidated application API, guidance for how the protocol's extension points should be used, and a few concrete examples of both core protocol extensions and uses of the application API. About This Document The latest revision of this draft can be found at . Status information for this document may be found at . Discussion of this document takes place on the Messaging Layer Security Working Group mailing list (), which is archived at . Subscribe at . Source for this draft and an issue tracker can be found at .

Introduction This document defines extensions to MLS that are not part of the main protocol specification, and uses them to explain how to extend the core operation of the MLS protocol. It also describes how applications can safely interact with MLS to take advantage of security features of MLS. The MLS protocol is designed to be integrated into applications in order to provide security services that the application requires. There are two questions to answer when designing such an integration:

1. How does the application provide the services that MLS requires?
2. How does the application use MLS to get security benefits?

The MLS Architecture describes the requirements for the first of these questions, namely the structure of the Delivery Service and Authentication Service that MLS requires. The next section of this document focuses on the second question. MLS itself offers some basic functions that applications can use, such as the secure message encapsulation (PrivateMessage), the MLS exporter, and the epoch authenticator. Current MLS applications make use of these mechanisms to achieve a variety of confidentiality and authentication properties. As application designers become familiar with MLS, there is interest in leveraging other cryptographic tools that an MLS group provides:

• HPKE (Hybrid Public Key Encryption ) and signature key pairs for each member, where the private key is known only to that member, and the public key is authenticated to the other members.
• A pre-shared key mechanism that can allow an application to inject data into the MLS key schedule.
• An exporter mechanism that allows applications to derive secrets from the MLS key schedule.
• Association of data with Commits as a synchronization mechanism.
• Binding of information to the GroupContext to confirm group agreement.

There is also interest in exposing an MLS group to multiple loosely coordinated components of an application. To accommodate such cases, the above mechanisms need to be exposed in such a way that the usage of different components do not conflict with each other, or with MLS itself. This document defines a set of mechanisms that application components can use to ensure that their use of these facilities is properly domain-separated from MLS itself, and from other application components that might be using the same MLS group.

Conventions and Definitions The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 when, and only when, they appear in all capitals, as shown here. This document makes heavy use of the terminology and the names of structs in the MLS specification . In addition, we introduce the following new terms:

Application:

The system that instantiates, manages, and uses an MLS group. Each MLS group is used by exactly one application, but an application may maintain multiple groups. This does not imply that it need be part of the Application Layer of the networking stack.

Application component:

A subsystem of an application that has access to an MLS group.

Component ID:

An identifier for an application component. These identifiers are assigned by the application.

Developing Extensions for the MLS Protocol MLS is highly extensible and was designed to be used in a variety of different applications. As such, it is important to separate extensions that change the behavior of an MLS stack, and application usages of MLS that just take advantage of features of MLS or specific extensions (hereafter referred to as components). Furthermore, it is essential that application components do not change the security properties of MLS or require new security analysis of the MLS protocol itself.

The Safe Application Interface The mechanisms in this section take MLS mechanisms that are either not inherently designed to be used by applications, or not inherently designed to be used by multiple application components, and adds a domain separator that separates application usage from MLS usage, and application components' usage from each other:

• Public-key encryption operations are tagged so that encrypted data will only decrypt in the context of a given component.
• Signing operations are similarly tagged so that signatures will only verify in the context of a given component.
• Exported values include an identifier for the component to which they are being exported, so that different components will get different exported values.
• Pre-shared keys are identified as originating from a specific component, so that different components' contributions to the MLS key schedule will not collide.
• Additional Authenticated Data (AAD) can be domain separated by component.

Similarly, the content of application messages (application_data) can be distinguished and routed to different parts of an application according to the media type of that content using the content negotiation mechanism defined in . We also define new general mechanisms that allow applications to take advantage of the extensibility mechanisms of MLS without having to define extensions themselves:

• An app_data_dictionary extension type that associates application data with MLS messages or with the state of the group.
• An AppEphemeral proposal type that enables arbitrary application data to be associated with a Commit.
• An AppDataUpdate proposal type that enables efficient updates to an app_data_dictionary GroupContext extension.

As with the above, information carried in these proposals and extensions is marked as belonging to a specific application component, so that components can manage their information independently. The separation between components is achieved by the application assigning each component a unique component ID number. These numbers are then incorporated into the appropriate calculations in the protocol to achieve the required separation.

Component IDs A component ID is a two-byte value that uniquely identifies a component within the scope of an application. When a label is required for an operation, the byte string resulting from the TLS Presentation Language encoding of the following data structure is used. The base_label field is always the fixed string "MLS Component". Thecomponent_id field identifies the component performing the operation. The label field identifies the operation being performed. ; /* = "MLS Component" */ ComponentID component_id; opaque label; } ComponentOperationLabel; ]]>

Hybrid Public Key Encryption (HPKE) Keys This part of the Safe Application Interface allows components to make use of the HPKE key pairs generated by MLS. A component identified by a ComponentID can use any HPKE key pair for any operation defined in , such as encryption, exporting keys, and the PSK mode, as long as the info input to Setup<MODE>S and Setup<MODE>R is set to ComponentOperationLabel with component_id set to the appropriate ComponentID. The context can be set to an arbitrary Context specified by the application designer and can be empty if not needed. For example, a component can use a key pair PublicKey, PrivateKey to encrypt data as follows: Where the fields of ComponentOperationLabel are set to For operations involving the secret key, ComponentID MUST be set to the ComponentID of the component performing the operation, and not to the ID of any other component. In particular, this means that a component cannot decrypt data meant for another component, while components can encrypt data that other components can decrypt. In general, a ciphertext encrypted with a PublicKey can be decrypted by any entity who has the corresponding PrivateKey at a given point in time according to the MLS protocol (or application component). For convenience, the following list summarizes lifetimes of MLS key pairs.

• The key pair of a non-blank ratchet tree node. The PrivateKey of such a key pair is known to all members in the node’s subtree. In particular, a PrivateKey of a leaf node is known only to the member in that leaf. A member in the subtree stores the PrivateKey for a number of epochs, as long as the PublicKey does not change. The key pair of the root node SHOULD NOT be used, since the external key pair recalled below gives better security.
• The external_priv, external_pub key pair used for external initialization. The external_priv key is known to all group members in the current epoch. A member stores external_priv only for the current epoch. Using this key pair gives better security guarantees than using the key pair of the root of the ratchet tree and should always be preferred.
• The init_key in a KeyPackage and the corresponding secret key. The secret key is known only to the owner of the KeyPackage and is deleted immediately after it is used to join a group.

Signature Keys MLS session states contain a number of signature keys including the ones in the LeafNode structs. Application components can safely sign content and verify signatures using these keys via the SafeSignWithLabel and SafeVerifyWithLabel functions, respectively, much like how the basic MLS protocol uses SignWithLabel and VerifyWithLabel. In more detail, a component identified by ComponentID should sign and verify using: Where the fields of ComponentOperationLabel are set to For signing operations, the ComponentID MUST be set to the ComponentID of the component performing the signature, and not to the ID of any other component. This means that a component cannot produce signatures in place of another component. However, components can verify signatures computed by other components. Domain separation is ensured by explicitly including the ComponentID with every operation.

Exported Secrets The MLS Exporter functionality described in does not provide forward security for exported secrets, because the exporter_secret is not deleted after a secret has been derived. In this section, we define a forward-secure exporter for use by application components. The safe exporter is constructed from an Exporter Tree, a tree of secrets with the same structure as the Secret Tree defined in , with two differences: First, an Exporter Tree always has 2¹⁶ leaves, corresponding to the 16 bits of a ComponentID value. (As with the Secret Tree, the nodes of the tree can be generated on-demand, for space-efficiency.) Second, the root of the Exporter Tree is the application_export_secret, an additional secret derived from the epoch_secret at the beginning of the epoch in the same way as the other secrets listed in Table 4 of using the label "application_export". This tree defines one exported secret per ComponentID. The secret for a ComponentID is the tree_node_secret at the leaf node for that ComponentID: Upon generating an exported secret for a component, the MLS implementation MUST regard that component's exported secret as "consumed", and delete any source key material according to the deletion schedule in .

Pre-Shared Keys (PSKs) PSKs represent key material that is injected into the MLS key schedule when creating or processing a commit as defined in . Its injection into the key schedule means that all group members have to agree on the value of the PSK. While PSKs are typically cryptographic keys which due to their properties add to the overall security of the group, the PSK mechanism can also be used to ensure that all members of a group agree on arbitrary pieces of data represented as octet strings (without the necessity of sending the data itself over the wire). For example, a component can use the PSK mechanism to enforce that all group members have access to and agree on a password or a shared file. This is achieved by creating a new epoch via a PSK proposal. Transitioning to the new epoch requires using the information agreed upon. To facilitate using PSKs safely, this document defines a new PSKType for application components. This provides domain separation between pre-shared keys used by the core MLS protocol and applications, and between those used by different components. ; }; opaque psk_nonce; } PreSharedKeyID; ]]>

Attaching Application Data to MLS Messages The MLS GroupContext, LeafNode, KeyPackage, and GroupInfo objects each have an extensions field that can carry additional data not defined by the MLS specification. The app_data_dictionary extension provides a generic container that applications can use to attach application data to these messages. Each usage of the extension serves a slightly different purpose:

• GroupContext: Confirms that all members of the group agree on the application data, and automatically distributes it to new joiners.
• KeyPackage and LeafNode: Associates the application data to a particular client, and advertises it to the other members of the group.
• GroupInfo: Distributes the application data confidentially to the new joiners for whom the GroupInfo is encrypted (as a Welcome message).

The content of the app_data_dictionary extension is a serialized AppDataDictionary object: ; } ComponentData; struct { ComponentData component_data; } AppDataDictionary; ]]> The entries in the component_data MUST be sorted by component_id, and there MUST be at most one entry for each component_id. An app_data_dictionary extension in a LeafNode, KeyPackage, or GroupInfo can be set when the object is created. The creator of the group can set an app_data_dictionary extension in the GroupContext unilaterally. Thereafter, the AppDataUpdate proposal described in the next section is the only way to change it. A GroupContextExtensions proposal leaves it as it is. Every implementation that advertises support for the app_data_dictionary extension MUST understand the app_components component defined in and the safe_aad component defined in .

Updating Application Data in the GroupContext Updating the app_data_dictionary with a GroupContextExtensions proposal is cumbersome. The application data needs to be transmitted in its entirety, along with any other extensions, whether or not they are being changed. And a GroupContextExtensions proposal always requires an UpdatePath, which updating application state never should. The AppDataUpdate proposal allows the app_data_dictionary extension to be updated without these costs. Instead of sending the whole value of the extension, it sends only an update, which is interpreted by the application to provide the new content for the app_data_dictionary extension. No other extensions are sent or updated, and no UpdatePath is required. ; case remove: struct{}; }; } AppDataUpdate; ]]> An AppDataUpdate proposal is invalid if its component_id references a component that is not known to the application, or if it specifies the removal of state for a component_id that has no state present. A proposal list is invalid if it includes multiple AppDataUpdate proposals that remove state for the same component_id, or proposals that both update and remove state for the same component_id. In other words, for a given component_id, a proposal list is valid only if it contains (a) a single remove operation or (b) one or more update operations. The rules in further restrict which components the app_data_dictionary extension in the GroupContext can include. The components defined in this document are updated as described in . AppDataUpdate proposals are processed after any default proposals (i.e., those defined in ), and any AppEphemeral proposals (defined in ). A GroupContextExtensions proposal MUST NOT add, remove, or modify the app_data_dictionary GroupContext extension, whether or not the AppDataUpdate proposal type is listed in the proposal_types list of the group's required_capabilities extension. A GroupContextExtensions proposal replaces the whole extensions list of the GroupContext (), so it carries the app_data_dictionary extension of the GroupContext of the current epoch unchanged, or omits it if that GroupContext has none. A GroupContextExtensions proposal is invalid if its app_data_dictionary extension is not identical to the one in the GroupContext of the current epoch, or if only one of the two has such an extension. This way, every change to the state of a component goes through the AppDataUpdate processing described below. Changing the app_data_dictionary extension after creation therefore requires that every member that processes the Commit supports the AppDataUpdate proposal, except members removed by that Commit (). A commit can contain a GroupContextExtensions proposal which modifies GroupContext extensions other than app_data_dictionary, and zero or more AppDataUpdate proposals. This allows modifications to both the app_data_dictionary extension (via AppDataUpdate) and other extensions (via GroupContextExtensions) in the same Commit. A client applies AppDataUpdate proposals by component ID. For each component_id field that appears in an AppDataUpdate proposal in the Commit, the client assembles a list of AppDataUpdate proposals with that component_id, in the order in which they appear in the Commit, and processes them in the following way:

• If the list comprises a single proposal with the op field set to remove:
  • If there is an entry in the component_data vector in the app_data_dictionary extension with the specified component_id, remove it.
  • Otherwise, the proposal is invalid.
• If the list comprises one or more proposals, all with op field set to update:
  • Provide the application logic registered to the component_id value with the content of the update field from each proposal, in the order specified.
  • The application logic returns either an opaque value new_data that will be stored as the new application data for this component, or else an indication that it considers this update invalid.
  • If the application logic considers the update invalid, the MLS client MUST consider the proposal list invalid.
  • If no app_data_dictionary extension is present in the GroupContext, add one to the end of the extensions list in the GroupContext.
  • If there is an entry in the component_data vector in the app_data_dictionary extension with the specified component_id, then set its data field to the specified new_data.
  • Otherwise, insert a new entry in the component_data vector with the specified component_id and the data field set to the new_data value. The new entry is inserted at the proper point to keep the component_data vector sorted by component_id.
• Otherwise, the proposal list is invalid.

• NOTE: Putting large amounts of data into the app_data_dictionary GroupContext extension may have a performance impact.

AppDataUpdate proposals do not require an UpdatePath. An AppDataUpdate proposal can be sent by an external sender. Likewise, AppDataUpdate proposals can be included in an external Commit. Applications can make more restrictive validity rules for the update of their components, such that some components would not be valid at the application when sent in an external Commit or via an external proposer. To avoid storing large amounts of data in the app_data_dictionary GroupContext extension, implementations MAY offer storing only a hash of the actual data in the GroupContext extension.

Attaching Application Data to a Commit The AppEphemeral proposal type allows an application component to associate application data to a Commit, so that the member processing the Commit knows that all other group members will be processing the same data. AppEphemeral proposals are ephemeral in the sense that they do not change any persistent state related to MLS, aside from their appearance in the transcript hash. The content of an AppEphemeral proposal is a single component_id and the data for that component. The proposal type is set in . ; } AppEphemeral; ]]> An AppEphemeral proposal is invalid if it contains a component_id that is unknown to the application, or if the data field is considered invalid by the application logic registered to the indicated component_id. AppEphemeral proposals MUST be processed after any default proposals (i.e., those defined in ), but before any AppDataUpdate proposals. A client applies an AppEphemeral proposal by providing the data field to the component identified by the component_id. If a Commit references more than one AppEphemeral proposal for the same component_id value, then they MUST be processed in the order in which they are specified in the Commit. AppEphemeral proposals do not require an UpdatePath. An AppEphemeral proposal can be sent by an external sender. Likewise, AppEphemeral proposals can be included in an external Commit. Applications can make more restrictive validity rules for ephemeral updates of their components, such that some components would not be valid at the application when sent in an external Commit or via an external proposer.

Safe Additional Authenticated Data (AAD) Both MLS PublicMessage and PrivateMessage messages can contain arbitrary additional application-specific data. The corresponding authenticated_data field that conveys this application-specific data appears in the FramedContent struct for PublicMessage and directly in the PrivateMessage struct. In an MLS PrivateMessage, the authenticated_data is also present in intermediary structs: in the FramedContent, which is used to generate the message signature and tags, and in the PrivateContentAAD, which is used as the AAD input to the PrivateMessage.ciphertext. The Safe AAD framing allows multiple application components to add AAD safely to the authenticated_data without conflicts or ambiguity. If the safe_aad component in the app_data_dictionary extension is present in the GroupContext (see ), the entire authenticated_data field is framed as a SafeAAD struct such that the elements of aad_items are sorted in increasing numerical order of the component_id. The struct is described below: ; } SafeAADItem; struct { SafeAADItem aad_items; } SafeAAD; ]]> If safe_aad is present, but none of the "safe" AAD components have data to send in a particular message, the aad_items is a zero-length vector.

Negotiating Extensions and Components MLS defines a Capabilities struct for LeafNodes (in turn used in KeyPackages), which describes which extensions are supported by the associated node. However, that struct (defined in ) only has fields for a subset of the extensions possible in MLS, as reproduced below. ; CipherSuite cipher_suites; ExtensionType extensions; ProposalType proposals; CredentialType credentials; } Capabilities; ]]>

• The "MLS Extension Types" registry represents extensibility of four core structs (GroupContext, GroupInfo, KeyPackage, and LeafNode) that have far reaching effects on the use of the protocol. The majority of MLS extensions in extend one or more of these core structs.

Likewise, the required_capabilities GroupContext extension (defined in and reproduced below) contains all non-default extensions that are mandatory to support in its extension_types vector. Its proposal_types vector contains any Proposals that are mandatory to support. Its credential_types vector contains any mandatory credential types. ; ProposalType proposal_types; CredentialType credential_types; } RequiredCapabilities; ]]> Due to an oversight in , the Capabilities struct does not include MLS Wire Formats. Instead, this document defines two extensions: supported_wire_formats (which can appear in LeafNodes), and required_wire_formats (which can appear in the GroupContext). ; } WireFormats; WireFormats supported_wire_formats; WireFormats required_wire_formats; ]]> This document also defines new components of the app_data_dictionary extension for supported and required Safe AAD, media types, and components. The safe_aad component contains a list of component IDs. When present (in an app_data_dictionary extension) in a LeafNode, the semantics are the list of supported components that use Safe AAD. When present (in an app_data_dictionary extension) in the GroupContext, the semantics are the list of required Safe AAD components (those that must be understood by the entire group). If the safe_aad component is present, even with an empty list, (in the app_data_dictionary extension) in the GroupContext, then the authenticated_data field is a SafeAAD struct as defined in . ; } ComponentsList; ComponentsList safe_aad; ]]> The list of required and supported components follows the same model with the new component app_components. When present in a LeafNode, the semantics are the list of supported components. When present in the GroupContext, the semantics are the list of required components. A LeafNode that does not list a component in app_components is treated as not supporting it. A safe_aad or app_components component that is absent from a LeafNode is equivalent to one with an empty list. Support for the app_components and safe_aad components themselves is implied by support for the app_data_dictionary extension (see ), so they are not listed, and an entry for either of them in a list is ignored. A component that uses Safe AAD is listed in both app_components and safe_aad. A LeafNode is invalid if its app_data_dictionary extension contains an entry for a component other than app_components and safe_aad that is not listed in its app_components component, just as it is invalid if it contains a non-default extension that its capabilities field does not list (). This check is part of LeafNode validation, so it applies wherever a LeafNode is validated, including the LeafNode in a KeyPackage. The required components in the GroupContext are enforced in the same way as the required_capabilities extension ():

• A LeafNode in a group is invalid if the app_components or safe_aad component in the GroupContext lists a component that the corresponding component in the LeafNode does not list. This check is part of LeafNode validation (), so it applies wherever a LeafNode is validated, against the GroupContext of the epoch in which the validation takes place. A LeafNode in a proposal or in the UpdatePath of a Commit is therefore checked against the GroupContext before the Commit.
• A client MUST NOT join a group whose GroupContext requires a component that the client does not support.
• A Commit is invalid if the GroupContext of the resulting epoch requires a component that a member of the resulting epoch does not list in the corresponding component of its LeafNode.
• A GroupContext is invalid if its app_data_dictionary extension contains an entry for a component other than app_components and safe_aad that is not listed in app_components. This applies when a group is created, to the GroupContext of the epoch resulting from a Commit, and to the GroupContext a new member receives. Because a Commit is judged by its resulting epoch, a single Commit can both require a component and set its state, in any order of proposals.

Finally, the supported and required media types (formerly called MIME types) are communicated in the content_media_types component (see ).

Updating the Components Defined in This Document The app_components, safe_aad, and content_media_types entries in the GroupContext are updated with AppDataUpdate proposals, following the rules in . For these components, the MLS implementation takes the place of the application logic:

• The update field of an update proposal contains the complete new value of the entry, encoded as the entry itself is: a ComponentsList for app_components and safe_aad, and a MediaTypeList for content_media_types. The proposal is invalid if the field does not decode as such.
• If a Commit contains several update proposals for one of these components, the value of the last one in the Commit becomes the new entry.
• A remove proposal deletes the entry.

GREASE The "Generate Random Extensions And Sustain Extensibility" (GREASE) approach is described in . Further, says that:

• "As discussed in Section 13, unknown values in capabilities MUST be ignored, and the creator of a capabilities field SHOULD include some random GREASE values to help ensure that other clients correctly ignore unknown values."

This specification adds the following locations where GREASE values for components can be included:

• LeafNode.extensions.app_data_dictionary.safe_aad
• LeafNode.extensions.app_data_dictionary.app_components
• LeafNode.extensions.app_data_dictionary
• KeyPackage.extensions.app_data_dictionary
• GroupInfo.extensions.app_data_dictionary

Unknown values (including GREASE values) in any of these fields MUST be ignored by receivers. A random selection of GREASE values SHOULD be included in any of these fields that would otherwise be present. Ignoring an unknown component does not skip the LeafNode check in . A GREASE entry in a LeafNode's app_data_dictionary extension is therefore listed in the LeafNode's app_components as well.

Extensions

AppAck An AppAck object is used to acknowledge receipt of application messages. Though this information implies no change to the group, it is conveyed inside an AppEphemeral Proposal with a component ID app_ack, so that it is included in the group's transcript by being included in Commit messages. ; } AppAck; ]]> An AppAck represents a set of messages received by the sender in the current epoch. Messages are represented by the sender and generation values in the PrivateMessage for the message. Each MessageRange represents receipt of a span of messages whose generation values form a continuous range from first_generation to last_generation, inclusive. AppAck objects are sent as a guard against the Delivery Service dropping application messages. The sequential nature of the generation field provides a degree of loss detection, since gaps in the generation sequence indicate dropped messages. AppAck completes this story by addressing the scenario where the Delivery Service drops all messages after a certain point, so that a later generation is never observed. Obviously, there is a risk that AppAck messages could be suppressed as well, but their inclusion in the transcript means that if they are suppressed then the group cannot advance at all.

Content Advertisement

Description This section defines a minimal framing format so MLS clients can signal which media type is being sent inside the MLS application_data object when multiple formats are permitted in the same group. It also defines a new content_media_types application component which is used to indicate support for specific formats, using the extensive IANA Media Types registry (formerly called MIME types). When the content_media_types component is present (in the app_data_dictionary extension) in a LeafNode, it indicates that node's support for a particular (non-empty) list of media types. When the content_media_types component is present (in the app_data_dictionary extension) in the GroupContext, it indicates a (non-empty) list of media types that need to be supported by all members of that MLS group, and that the application_data will be framed using the application framing format described later in . This allows clients to confirm that all members of a group can communicate.

• Note that when the membership of a group changes, or when the policy of the group changes, it is responsibility of the committer to ensure that the membership and policies are compatible.

As clients are upgraded to support new formats they can use these extensions to detect when all members support a new or more efficient encoding, or select the relevant format or formats to send. Vendor-specific media subtypes starting with vnd. can be registered with IANA without standards action as described in . Implementations which wish to send multiple formats in a single application message, may be interested in the multipart/alternative media type defined in or may use or define another type with similar semantics (for example using TLS Presentation Language syntax ).

• Note that the usage of IANA media types in general does not imply the usage of MIME Headers for framing.

Syntax MediaType is a TLS encoding of a single IANA media type (including top-level type and subtype) and any of its parameters. A parameter_value consists of US-ASCII visible characters (hex 0x21 to 0x7E), space (0x20), and horizontal tab (0x09). Even if the parameter_value would have required formatting as a quoted-string or quoted-pair in a text encoding, only the unescaped, unquoted contents are included in parameter_value. MediaTypeList is an ordered list of MediaType objects. ; /* Note: parameter_value never includes the quotation marks of */ /* an RFC 2045 quoted-string or the first "\" of a quoted-pair */ opaque parameter_value; } Parameter; struct { /* type is an IANA top-level media type, a "/" character, * and the IANA media subtype */ opaque type; /* a list of zero or more parameters defined for the subtype */ Parameter parameters; } MediaType; struct { /* must contain at least one item */ MediaType media_type_list; } MediaTypeList; MediaTypeList content_media_types; ]]> Example IANA media types with optional parameters: For the example media type for text/plain, the media_type.type field would be text/plain, media_type.parameters would contain a single Parameter with a parameter_name of charset and a parameter_value of UTF-8.

Expected Behavior An MLS client which implements this section SHOULD include the content_media_types component (in the app_data_dictionary extension) in its LeafNodes, with a media_type_list vector listing all the media types it can receive. As requires, the client also includes content_media_types in the app_components list (in the app_data_dictionary extension), and support for the app_data_dictionary extension in its capabilities.extensions field in its LeafNodes (including in LeafNodes inside its KeyPackages). When creating a new MLS group for an application using this specification, the group MAY include a content_media_types component (in the app_data_dictionary extension) in the GroupContext. In that case the GroupContext also lists content_media_types in its app_components component, as requires. Later changes to the component use AppDataUpdate proposals as described in . (The creating client also includes its content_media_types component in its own LeafNode as described in the previous paragraph.) MLS clients SHOULD NOT add an MLS client to an MLS group with content_media_types in its GroupContext unless all the members (after taking into account any membership changes in the valid pending Proposals) advertise support for all the required media types. As an exception, a client could be preconfigured to know that certain clients support the required types. Likewise, an MLS client is already forbidden from issuing or committing a GroupContextExtensions Proposal which introduces required extensions which are not supported by all members in the resulting epoch.

Framing of application_data When an MLS group contains the content_media_types component (in the app_data_dictionary extension) in its GroupContext, the application_data sent in that group is interpreted as ApplicationFraming as defined below: ; } ApplicationFraming; ]]> The media_type.type MAY be zero length, in which case, the media type of the inner_application_content is interpreted as the first MediaType specified in the content_media_types component in the GroupContext.

SelfRemove Proposal The design of the MLS protocol prevents a member of an MLS group from removing itself immediately from the group. (To cause an immediate change in the group, a member must send a Commit message. However, the sender of a Commit message knows the keying material of the new epoch and therefore needs to be part of the group.) Instead, a member wishing to remove itself can send a Remove Proposal and wait for another member to Commit its Proposal. Unfortunately, MLS clients that join via an external Commit ignore pending, but otherwise valid, Remove Proposals. The member trying to remove itself has to monitor the group and send a new Remove Proposal in every new epoch until the member is removed. In a group with a burst of external joiners, a member connected over a high-latency link (or one that is merely unlucky) might have to wait several epochs to remove itself. A real-world situation in which this happens is a member trying to remove itself from a conference call as several dozen new participants are trying to join (often on the hour). This section describes a new SelfRemove proposal type. It is designed to be included in external Commits.

Proposal Description This document specifies a new MLS Proposal type called SelfRemove. Its syntax is described using the TLS Presentation Language below (its content is an empty struct). It is allowed in external Commits and requires an UpdatePath. SelfRemove proposals are only allowed in a Commit by reference. SelfRemove cannot be sent as an external proposal. The struct above reproduces the Proposal type from with the self_remove case added to show where SelfRemove fits. It is not the complete extended set: the app_ephemeral and app_data_update proposal types defined in this document extend the same enum. The description of behavior below only applies if all the members of a group support this proposal in their capabilities; such a group is a "self-remove-capable group". An MLS client which supports this proposal can send a SelfRemove Proposal whenever it would like to remove itself from a self-remove-capable group. Because the point of a SelfRemove Proposal is to be available to external joiners (which are not yet members), these proposals MUST be sent in an MLS PublicMessage. Whenever a member receives a SelfRemove Proposal, it includes it along with any other pending Proposals when sending a Commit. It already MUST send a Commit of pending Proposals before sending new application messages. When a member receives a Commit referencing one or more SelfRemove Proposals, it treats the proposal like a Remove Proposal, except the leaf node to remove is determined by looking in the Sender leaf_index of the original Proposal. The member is able to verify that the Sender was a member. Whenever a new joiner is about to join a self-remove-capable group with an external Commit, the new joiner MUST fetch any pending SelfRemove Proposals along with the GroupInfo object, and include the SelfRemove Proposals in its external Commit by reference. (An external Commit can contain zero or more SelfRemove proposals). The new joiner MUST validate the SelfRemove Proposal before including it by reference, except that it skips the validation of the membership_tag because a non-member cannot verify membership. During validation, SelfRemove proposals are processed after Update proposals and before Remove proposals. If there is a pending SelfRemove proposal for a specific leaf node and a pending Remove proposal for the same leaf node, the Remove proposal is invalid. A client MUST NOT issue more than one SelfRemove proposal per epoch. The MLS Delivery Service (DS) needs to validate SelfRemove Proposals it receives (except that it cannot validate the membership_tag). If the DS provides a GroupInfo object to an external joiner, the DS SHOULD attach any SelfRemove proposals known to the DS to the GroupInfo object. As with Remove proposals, clients need to be able to receive a Commit message which removes them from the group via a SelfRemove. If the DS does not forward a Commit to a removed client, it needs to inform the removed client out-of-band.

Last-Resort KeyPackages Type: KeyPackage component

Description details that clients are required to pre-publish KeyPackages so that other clients can add them to groups asynchronously. It also states that they should not be re-used:

• KeyPackages are intended to be used only once and SHOULD NOT be reused except in the case of a "last resort" KeyPackage (see Section 16.8). Clients MAY generate and publish multiple KeyPackages to support multiple cipher suites.

then introduces the notion of last-resort KeyPackages as follows:

• An application MAY allow for reuse of a "last resort" KeyPackage in order to prevent denial-of-service attacks.

However, does not specify how to distinguish regular KeyPackages from last-resort ones. The last_resort_key_package KeyPackage application component defined in this section fills this gap and allows clients to specifically mark KeyPackages as KeyPackages of last resort that MAY be used more than once in scenarios where all other KeyPackages have already been used. The component allows clients that pre-publish KeyPackages to signal to the Delivery Service which KeyPackage(s) are meant to be used as last-resort KeyPackages. An additional benefit of using a component rather than communicating the information out-of-band is that the component is still present in Add proposals. Clients processing such Add proposals can authenticate that a KeyPackage is a last-resort KeyPackage and MAY make policy decisions based on that information.

Format The purpose of the application component is simply to mark a given KeyPackage, which means it carries no additional data. As a result, a last_resort_key_package component contains the component_id with an empty data field.

Multi-Credentials Multi-credentials address use cases where there might not be a single credential that captures all of a client's authenticated attributes. For example, an enterprise messaging client may wish to provide attributes both from its messaging service, to prove that its user has a given handle in that service, and from its corporate owner, to prove that its user is an employee of the corporation. Multi-credentials can also be used in migration scenarios, where some clients in a group might wish to rely on a newer type of credential, but other clients haven't yet been upgraded. New credential types MultiCredential and WeakMultiCredential are defined as shown below. These credential types are indicated with the values multi and weak-multi (see ). ; } CredentialBinding; struct { CredentialBinding bindings; } MultiCredential; struct { CredentialBinding bindings; } WeakMultiCredential; ]]> The two types of credentials are processed in exactly the same way. The only difference is in how they are treated when evaluating support by other clients, as discussed below.

Credential Bindings A multi-credential consists of a collection of "credential bindings". Each credential binding is a signed statement by the holder of the credential that the signature key in the LeafNode belongs to the holder of that credential. Specifically, the signature is computed using the MLS SignWithLabel function, with label "CredentialBindingTBS" and with a content that covers the contents of the CredentialBinding, plus the signature_key field from the LeafNode in which this credential will be embedded. The cipher_suite for a credential is NOT REQUIRED to match the cipher suite for the MLS group in which it is used, but MUST meet the support requirements with regard to support by group members discussed below.

Verifying a Multi-Credential A credential binding is supported by a client if the client supports the credential type and cipher suite of the binding. A credential binding is valid in the context of a given LeafNode if all of the following are true:

• The credential is valid according to the MLS Authentication Service.
• The credential_key corresponds to the specified credential, in the same way that the signature_key would have to correspond to the credential if the credential were presented in a LeafNode.
• The signature field is valid with respect to the signature_key value in the leaf node.

A client that receives a credential of type multi in a LeafNode MUST verify that all of the following are true:

• All members of the group support credential type multi.
• For each credential binding in the multi-credential:
  • Every member of the group supports the cipher suite and credential type values for the binding.
  • The binding is valid in the context of the LeafNode.

A client that receives a credential of type weak-multi in a LeafNode MUST verify that all of the following are true:

• All members of the group support credential type weak-multi.
• Each member of the group supports at least one binding in the multi-credential. (Different members may support different subsets.)
• Every binding that this client supports is valid in the context of the LeafNode.

IANA Considerations This document requests the addition of various new values under the heading of "Messaging Layer Security". Each registration is organized under the relevant registry Type. This document also requests the creation of a new "MLS Component Types" registry as described in . RFC EDITOR: Please replace XXXX throughout with the RFC number assigned to this document

MLS Extension Types

app_data_dictionary MLS Extension The app_data_dictionary MLS Extension Type is used inside KeyPackage, LeafNode, GroupContext, or GroupInfo objects. It contains a sorted list of application component data objects (at most one per component).

• Value: 0x0006 (suggested)
• Name: app_data_dictionary
• Message(s): KP: This extension may appear in KeyPackage objects LN: This extension may appear in LeafNode objects GC: This extension may appear in GroupContext objects GI: This extension may appear in GroupInfo objects
• Recommended: Y
• Reference: RFC XXXX

supported_wire_formats MLS Extension The supported_wire_formats MLS Extension Type is used inside LeafNode objects. It contains a list of non-default Wire Formats supported by the client node.

• Value: 0x0007 (suggested)
• Name: supported_wire_formats
• Message(s): LN: This extension may appear in LeafNode objects
• Recommended: Y
• Reference: RFC XXXX

required_wire_formats MLS Extension The required_wire_formats MLS Extension Type is used inside GroupContext objects. It contains a list of non-default Wire Formats that are mandatory for all MLS members of the group to support.

• Value: 0x0008 (suggested)
• Name: required_wire_formats
• Message(s): GC: This extension may appear in GroupContext objects
• Recommended: Y
• Reference: RFC XXXX

MLS Proposal Types

AppDataUpdate Proposal The app_data_update MLS Proposal Type is used to efficiently update application component data stored in the app_data_dictionary GroupContext extension.

• Value: 0x0008 (suggested)
• Name: app_data_update
• Recommended: Y
• External: Y
• Path Required: N

AppEphemeral Proposal The app_ephemeral MLS Proposal Type is used to send opaque ephemeral application data that needs to be synchronized with a specific MLS epoch.

• Value: 0x0009 (suggested)
• Name: app_ephemeral
• Recommended: Y
• External: Y
• Path Required: N

SelfRemove Proposal The self_remove MLS Proposal Type is used for a member to remove itself from a group more efficiently than using a remove proposal type, as the self_remove type is permitted in external Commits.

• Value: 0x000a (suggested)
• Name: self_remove
• Recommended: Y
• External: N
• Path Required: Y

MLS Credential Types

Multi-Credential

• Value: 0x0003 (suggested)
• Name: multi
• Recommended: Y
• Reference: RFC XXXX

Weak Multi-Credential

• Value: 0x0004 (suggested)
• Name: weak-multi
• Recommended: Y
• Reference: RFC XXXX

MLS Signature Labels

CredentialBindingTBS

• Label: "CredentialBindingTBS"
• Recommended: Y
• Reference: RFC XXXX

MLS Component Types This document requests the creation of a new IANA "MLS Component Types" registry under the "Messaging Layer Security" group registry heading. Assignments to this registry in the range 0x0000 to 0x7FFF are via Specification Required policy using the MLS Designated Experts. Assignments in the range 0x8000 to 0xFFFF are for private use. Template:

• Value: The numeric value of the component ID
• Name: The name of the component
• Where: The object(s) in which the component may appear, drawn from the following list:
  • AD: SafeAAD objects
  • AE: AppEphemeral proposals
  • ES: Exporter Secret labels
  • GC: GroupContext objects
  • GI: GroupInfo objects
  • HP: HPKE key labels
  • KP: KeyPackage objects
  • LN: LeafNode objects
  • PS: PSK labels
  • SK: Signature Key labels
• Recommended: Same as in
• Reference: The document where this component is defined

The restrictions noted in the "Where" column are to be enforced by the application. MLS implementations MUST NOT impose restrictions on where component IDs are used in which parts of MLS, unless specifically directed to by the application. Initial Contents:

Value	Name	Where	R	Ref
0x0000	RESERVED	N/A	-	RFC XXXX
0x0001	app_components	LN,GC	Y	RFC XXXX
0x0002	safe_aad	LN,GC	Y	RFC XXXX
0x0003	content_media_types	LN,GC	Y	RFC XXXX
0x0004	last_resort_key_package	KP	Y	RFC XXXX
0x0005	app_ack	AE	Y	RFC XXXX
0x0A0A	GREASE	Note1	Y	RFC XXXX
0x1A1A	GREASE	Note1	Y	RFC XXXX
0x2A2A	GREASE	Note1	Y	RFC XXXX
0x3A3A	GREASE	Note1	Y	RFC XXXX
0x4A4A	GREASE	Note1	Y	RFC XXXX
0x5A5A	GREASE	Note1	Y	RFC XXXX
0x6A6A	GREASE	Note1	Y	RFC XXXX
0x7A7A	GREASE	Note1	Y	RFC XXXX
0x8000 - 0xFFFF	Reserved for Private Use	N/A	N	RFC XXXX

• Note1: GREASE values for components MAY be present in GI, KP, and LN objects.

Security considerations

Safe Application Interface The Safe Application Interface provides the following security guarantee: If an application uses MLS with application components, the security guarantees of the base MLS protocol and the security guarantees of each application component analyzed in isolation, still hold for the composed application of the MLS protocol. In other words, the Safe Application Interface protects applications from careless component developers. It is not possible that a combination of components (the developers of which did not know about each other) impedes the security of the base MLS protocol or any other component. No further analysis of the combination is necessary. This also means that any security vulnerabilities introduced by one component do not spread to other components or the base MLS implementation.

AppAck When AppAck objects are received, they allow clients to detect if the Delivery Service (or an intermediary) dropped application messages, since gaps in the generation sequence indicate dropped messages. When AppAck messages are accepted by the Delivery Service, but not received by some members, the members who have missed the corresponding AppEphemeral proposals will not be able to send or receive a commit message, because the proposal is included in the transcript hash. Likewise, if AppAck objects and/or commits are sent periodically by every member, other members will be able to detect a member that is no longer sending on that schedule or whose handshake messages are being suppressed by the DS.

• Note: External Commits do not typically contain pending proposals (including AppEphemeral proposals). Clients that send an AppAck component in an AppEphemeral proposal will need to send a new AppAck component in an AppEphemeral proposal (in the new epoch) after receiving an external Commit until it has been incorporated into an accepted Commit.

The schedule on which AppAck objects are sent in AppEphemeral proposals is up to the application, and determines which cases of loss/suppression are detected. For example:

• The application might have the committer include an AppAck whenever a Commit is sent, so that other members could know when one of their messages did not reach the committer.
• The application could have a client send an AppAck whenever an application message is sent, covering all messages received since its last AppAck. This would provide a complete view of any losses experienced by active members.
• The application could simply have clients send AppAck proposals on a timer, so that all participants' state would be known.

An application using AppAck to guard against loss/suppression of application messages also needs to ensure that AppAck messages and the Commits that reference them are not dropped. One way to do this is to always encrypt Proposal and Commit messages, to make it more difficult for the Delivery Service to recognize which messages contain AppAcks. The application can also have clients enforce an AppAck schedule, reporting loss if an AppAck is not received at the expected time.

Content Advertisement Use of the content_media_types component could leak some private information visible in KeyPackages and inside an MLS group. This could be used to infer a specific implementation, platform, or even version. Clients should carefully consider the privacy implications in their environment of making a list of acceptable media types available. Implementations need to be prepared to parse media types containing long parameter lists, potentially containing characters which would be escaped or quoted in .

SelfRemove An external recipient of a SelfRemove Proposal cannot verify the membership_tag. However, an external joiner also has no way to completely validate a GroupInfo object that it receives. An insider can prevent an External Join by providing either an invalid GroupInfo object or an invalid SelfRemove Proposal. The security properties of external joins do not change with the addition of this proposal type.

Multi-Credentials Using a Weak Multi Credential reduces the overall credential security to the security of the least secure of its credential bindings.

References Normative References Messaging applications are increasingly making use of end-to-end security mechanisms to ensure that messages are only accessible to the communicating endpoints, and not to any servers involved in delivering messages. Establishing keys to provide such protections is challenging for group chat settings, in which more than two clients need to agree on a key but may not be online at the same time. In this document, we specify a key establishment protocol that provides efficient asynchronous group key establishment with forward secrecy (FS) and post-compromise security (PCS) for groups in size ranging from two to thousands. This document describes a scheme for hybrid public key encryption (HPKE). This scheme provides a variant of public key encryption of arbitrary-sized plaintexts for a recipient public key. It also includes three authenticated variants, including one that authenticates possession of a pre-shared key and two optional ones that authenticate possession of a key encapsulation mechanism (KEM) private key. HPKE works for any combination of an asymmetric KEM, key derivation function (KDF), and authenticated encryption with additional data (AEAD) encryption function. Some authenticated variants may not be supported by all KEMs. We provide instantiations of the scheme using widely used and efficient primitives, such as Elliptic Curve Diffie-Hellman (ECDH) key agreement, HMAC-based key derivation function (HKDF), and SHA2. This document is a product of the Crypto Forum Research Group (CFRG) in the IRTF. In many standards track documents several words are used to signify the requirements in the specification. These words are often capitalized. This document defines these words as they should be interpreted in IETF documents. This document specifies an Internet Best Current Practices for the Internet Community, and requests discussion and suggestions for improvements. RFC 2119 specifies common key words that may be used in protocol specifications. This document aims to reduce the ambiguity by clarifying that only UPPERCASE usage of the key words have the defined special meanings. This document specifies version 1.3 of the Transport Layer Security (TLS) protocol. TLS allows client/server applications to communicate over the Internet in a way that is designed to prevent eavesdropping, tampering, and message forgery. This document updates RFCs 5705 and 6066, and obsoletes RFCs 5077, 5246, and 6961. This document also specifies new requirements for TLS 1.2 implementations. Many protocols make use of points of extensibility that use constants to identify various protocol parameters. To ensure that the values in these fields do not have conflicting uses and to promote interoperability, their allocations are often coordinated by a central record keeper. For IETF protocols, that role is filled by the Internet Assigned Numbers Authority (IANA). To make assignments in a given registry prudently, guidance describing the conditions under which new values should be assigned, as well as when and how modifications to existing values can be made, is needed. This document defines a framework for the documentation of these guidelines by specification authors, in order to assure that the provided guidance for the IANA Considerations is clear and addresses the various issues that are likely in the operation of a registry. This is the third edition of this document; it obsoletes RFC 5226. This document specifies the Internet Message Format (IMF), a syntax for text messages that are sent between computer users, within the framework of "electronic mail" messages. This specification is a revision of Request For Comments (RFC) 2822, which itself superseded Request For Comments (RFC) 822, "Standard for the Format of ARPA Internet Text Messages", updating it to reflect current practice and incorporating incremental changes that were specified in other RFCs. [STANDARDS-TRACK] Informative References Inria & Mozilla Windy Hill Systems, LLC Wire The Messaging Layer Security (MLS) protocol (I-D.ietf-mls-protocol) provides a Group Key Agreement protocol for messaging applications. MLS is meant to protect against eavesdropping, tampering, message forgery, and provide Forward Secrecy (FS) and Post-Compromise Security (PCS). This document describes the architecture for using MLS in a general secure group messaging infrastructure and defines the security goals for MLS. It provides guidance on building a group messaging system and discusses security and privacy tradeoffs offered by multiple security mechanisms that are part of the MLS protocol (e.g., frequency of public encryption key rotation). The document also provides guidance for parts of the infrastructure that are not standardized by MLS and are instead left to the application. While the recommendations of this document are not mandatory to follow in order to interoperate at the protocol level, they affect the overall security guarantees that are achieved by a messaging application. This is especially true in the case of active adversaries that are able to compromise clients, the delivery service, or the authentication service. This document defines procedures for the specification and registration of media types for use in HTTP, MIME, and other Internet protocols. This memo documents an Internet Best Current Practice. This second document defines the general structure of the MIME media typing system and defines an initial set of media types. [STANDARDS-TRACK] This initial document specifies the various headers used to describe the structure of MIME messages. [STANDARDS-TRACK]

Change Log RFC EDITOR PLEASE DELETE THIS SECTION. draft-11

• enforce the required components in the GroupContext in the same way as the required_capabilities extension
• support for the app_components and safe_aad components is implied by support for the app_data_dictionary extension, and they are no longer listed in either component
• the app_data_dictionary extension in a GroupContext or LeafNode can only contain entries for components listed in its app_components component, including GREASE entries
• a GroupContextExtensions proposal can no longer change the app_data_dictionary extension, whether or not AppDataUpdate is a required proposal type
• define how AppDataUpdate proposals update the app_components, safe_aad, and content_media_types components
• clarify that proposal order does not matter for GroupContextExtensions and AppDataUpdate proposals in the same Commit
• restrict the characters allowed in a media type parameter_value

draft-10

• remove AppAck ProposalType as it is now a Component conveyed in AppEphemeral Proposals
• be more pedantic when discussing that a proposal in required_capabilities implies all clients support it but not vice versa.
• correct location of GREASE values for advertising safe_add and app_components in LeafNodes; only allow GREASE in GI, LN, and KP.
• the app_components component is now mandatory to implement if app_data_dictionary is supported.
• the safe_add component is now mandatory to understand if app_data_dictionary is supported.
• rename MediaType.media_type to MediaType.type, and MediaTypeList.media_types to MediaTypeList.media_type_list
• clarify the behavior of an "empty" media type in application framing: if media_type.type is zero length.
• unsafe AAD is no longer allowed when the safe_aad component is present in the GroupContext
• rename "Safe Application API" to "Safe Application Interface"
• fix IANA registry names ("MLS Component Types", "MLS Extension Types") and restore missing registry section headers
• correct stale field and struct names in prose (component_data, app_data_dictionary, authenticated_data, required_wire_formats)
• reclassify last-resort KeyPackages as a KeyPackage component and fix various inconsistencies and typos

draft-09

• rename the component base label from "Application" to "MLS Component"

draft-08

• clarify that SelfRemove is a proposal type, not an extension

draft-07

• add AppAck to IANA considerations
• adapt Safe AAD scope
• remove targeted messages altogether with intention to publish it as a separate document
• assign self_remove proposal to a non duplicate number (0x000a)
• refactor TargetedMessage to no longer use structs removed from when it was a "safe extension"
• remove the no-longer needed targeted_messages_capability (now signaled using support_wire_formats and required_wire_formats)
• add TargetedMessageTBS and CredentialBundleTBS to MLS Signature Labels IANA registry
• add GREASE values for components
• fix safe exporter definition
• resolve TODOs from -06
• fix numerous typos

draft-06

• Integrate notion of Application API from draft-barnes-mls-appsync

draft-05

• Include definition of ExtensionState extension
• Add safe use of AAD to Safe Extensions framework
• Clarify how capabilities negotiation works in Safe Extensions framework

draft-04

• No changes (prevent expiration)

draft-03

• Add Last Resort KeyPackage extension
• Add Safe Extensions framework
• Add SelfRemove Proposal

draft-02

• No changes (prevent expiration)

draft-01

• Add Content Advertisement extensions

draft-00

• Initial adoption of draft-robert-mls-protocol-00 as a WG item.
• Add Targeted Messages extension (*)

Contributors Amazon

alwenjo@amazon.com

Phoenix R&D

konrad.kohbrok@datashrine.de

Rohan Mahy Consulting Services

rohan.ietf@gmail.com

Amazon

mulmarta@amazon.com

Cisco Systems

rlb@ipv.sx