Abstract: Methods, systems, and devices for wireless communications are described. The method may include a user equipment (UE) may receive a control signal indicating an event trigger for reporting a performance parameter associated with a machine learning model. Further, the UE may receive one or more signals indicating input data for monitoring a performance of the machine learning model by the UE. Upon detecting the event trigger, the UE may transmit a report comprising the performance parameter.

Abstract: Man-in-the-middle attacks on reference signals used for positioning a mobile device in a wireless network can be detected through time and/or angle consistency checks. Time consistency checks may be based on a consistency of peak location and/or power delay profile across multiple reference signals and/or across different signal types, for example. Angle consistency checks may be based on a consistency of an angle at which a reference signal is received across multiple reference signals and/or in comparison with an expected angle, for example. Embodiments may further include reporting detected attacks.

Abstract: Methods, systems, and devices for wireless communications are described. A server (e.g., a network entity, a model repository) may select user equipment (UEs) to participate in a federated learning procedure for training a predictive model. Based on selecting the UEs, the server may determine a set of training parameters for a training configuration for the federated learning procedure. The server may transmit an indication of the training configuration to the UEs. The server may activate the federated learning procedure by transmitting an activation indication to the UEs. Each UE may locally train the predictive model according to the training configuration, and may report the model parameters to the server. The server may aggregate the reported model parameters into an updated model parameter set. The server may assign an updated parameter set identifier (PS ID) to the updated model parameter set and may inform the UEs of the updated PS ID.

Abstract: Methods, systems, and devices for wireless communications are described. In the context of a service-based wireless system, a user equipment (UE) may identify (e.g., via signaling from the network or based on a subscriber identity module (SIM)) a set of core network services offered by a service-based network that interfaces with a radio access network (RAN) associated with the network entity. Each of the respective core network services may be associated with a corresponding network address. The UE may transmit a service request to a network address associated with a core network service included within the set of offered core network services, and may receive a service context for communicating with the core network service in response to the service request. The UE may then communicate service messages with the core network service (via the network entity) in accordance with the received service context.

Abstract: Methods, systems, and devices for wireless communications are described. Described techniques relate to signaling between user equipment (UE), distributed units, and a transport service of a service-based network that provides radio bearers for multiple core network services of the service-based network. The transport service may enable the UE to establish and maintain connections with the various core network services offered by the service-based network. A UE may indicate requested parameters, such as quality of service (QoS) targets, an amount of data, and the like, and the transport service may return service information indicating core network services that match the request capabilities. A distributed unit may map one or multiple transport radio bearers to a logical channel, and provide a physical resource configuration to the UE for communicating with one or more core network services via the distributed unit.

Abstract: Methods, systems, and devices for wireless communications are described. In the context of a service-based wireless system, a user equipment (UE) may communicate with one or more core network services offered by a service-based network, where respective core network services are in one of an active, inactive, or unconnected state at the UE. The UE may be configured to maintain service contexts for communicating with core network services that are in an active or an inactive state at the UE, where signaling between the UE and each respective core network service may be used to activate or deactivate the respective core network services at the UE between the active and inactive states. By maintaining service contexts for inactive core network services, the UE may be able to quickly and efficiently resume communications with a core network service in accordance with the stored service context upon activating the core network service.

Abstract: Methods, systems, and devices for wireless communications are described. In the context of a service-based wireless system, a network entity of a random access network (RAN) may aggregate system information block (SIB) configurations from multiple core network services, where the core network services are offered or provided by a service-based network that interfaces with the RAN. After aggregating the SIB configurations, the network entity may relay or broadcast system information (e.g., SIB containers) to UEs communicatively coupled to the RAN on behalf of the core network services.

Abstract: Methods, systems, and devices for wireless communications are described. In the context of a service-based wireless system, a user equipment (UE) may receive signaling from a network entity indicating a set of core network services offered by a service-based network that interfaces with a radio access network (RAN) associated with the network entity. A capability service may obtain UE capabilities, and provide relevant capabilities to one or more other core network services. The UE may transmit an updated UE capability to the capability service, which may provide updated capability indications to one or more services that have subscribed to receive indications of updated UE capabilities.

Abstract: Methods, systems, and devices for wireless communications are described. Described techniques relate to signaling between user equipments (UEs), distributed units, and a discovery service of a service-based network that provides service information about other core network services of the service-based network. The service information may enable the UE to establish and maintain connections with the various core network services offered by the service-based network. A UE may indicate requested capabilities for the core network services, and the discovery service may return service information indicating core network services that match the requested capabilities. The UE may request information regarding specific core network services in the discovery request, and the discovery service may return information regarding the specific core network services.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may obtain generalization information associated with a model, a model structure (MS), or a parameter set (PS) associated with the model. The UE may initiate a connection to a network node. The UE may filter the model, the MS, or the PS based at least in part on the generalization information. The UE may transmit UE capability information to the network node, based at least in part on filtering the model, the MS or the PS, that indicates whether the model, the MS, or the PS is applicable, available, or supported by the UE. Numerous other aspects are described.

Abstract: Methods, systems, and devices for wireless communications are described. In a service-based network, groups of core network services may share a user equipment (UE) credential or network subscription. Signaling between a UE and a service-based network (e.g., via a distributed unit) enables the UE to establish a service context for communications with multiple core network services in a same service group. A UE may receive control signaling from the network indicating service groups offered by the service-based network. The control signaling may indicate the services included in each service group and how to access the service group. The UE may transmit an access request indicating a selected service group to the network, and in response, the network may indicate a service context for communicating with the services included in the service group. The UE may use the same service context to access the different services in the service group.

Abstract: Methods, systems, and devices for wireless communications are described. An end-to-end routing layer may address packets between a user equipment (UE) and core network services offered by a service-based network on a per-core network service basis. A UE may communicate directly with a core network service (e.g., based on a network address associated with the core network service) or indirectly (e.g., through a proxy service). The UE may select access stratum (AS) resources over which to transmit an uplink packet data unit based on the target core network service. The UE may receive control signaling from a distributed unit, a system information block (SIB), or point-to-point signaling from the core network services indicating specific AS resources for each core network service. The UE may select logical channels for transmitting the uplink packet data units to specific core network services based on the AS resources associated with each service.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a measurement configuration including trigger conditions for performance of handover procedures within a service-based wireless system. The UE may transmit a message indicating a satisfaction of a trigger condition to a source network entity, a mobility service offered by a service-based network, or both. After performance of a handover decision by the source network entity, the mobility service, or both, the mobility service may select a target network entity for the handover procedure. The mobility service may select a target network entity that supports at least one active core network service at the UE. The UE may then receive a handover command from the mobility service, and may perform a handover procedure to the target network entity.

Abstract: Methods, systems, and devices for wireless communications are described. In some examples, a wireless communications system may support machine learning and may configure a user equipment (UE) for machine learning. The UE may transmit, to a base station, a request message that includes an indication of a machine learning model or a neural network function based at least in part on a trigger event. In response to the request message, the base station may transmit a machine learning model, a set of parameters corresponding to the machine learning model, or a configuration corresponding to a neural network function and may transmit an activation message to the UE to implement the machine learning model and the neural network function.

Abstract: Aspects directed towards Quality of Service (QoS) flow remapping are disclosed. In an example, upon detecting a mapping reconfiguration of a first QoS flow from a first data radio bearer (DRB) to another DRB, a Service Data Adaptation Protocol (SDAP) control protocol data unit (PDU) is generated indicating that a final SDAP data PDU associated with the first QoS flow has been transmitted on the first DRB. The SDAP control PDU is then transmitted via the first DRB. In another example, upon detecting a mapping reconfiguration of a first QoS flow from a first DRB to another DRB, an end marker parameter is set in an SDAP header of a first SDAP data PDU received from an upper layer after the mapping reconfiguration indicating that the first SDAP data PDU is a final SDAP data PDU associated with the first QoS flow transmitted on the first DRB.

Abstract: Reference signals used in location estimation of a user equipment (UE) in a wireless data network can be secured against a man-in-the-middle attack by a transmitting device withholding the conveyance of transmission parameters for decoding portions of a reference signal until after the portions are transmitted. Thus, receiving devices can buffer received signals and, after receiving the transmission parameters, process the buffered signals. To further prevent an attacker device from attacking future reference signals, transmission parameters can be nondeterministic such that an attacker device obtaining a parameter at a certain period of time is unable to use the decoded parameter predict or determine subsequent transmission parameters.

Abstract: Example implementations include a method, apparatus and computer-readable medium of wireless communication by a user equipment (UE), comprising receiving parameter set configuration information from a network entity, the parameter set configuration information corresponding to a model structure employed in a machine learning operation by the UE for the wireless communication. The implementations further include activating a parameter set in response to an activation condition, the parameter set identified within the parameter set configuration information as being associated with the activation condition.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit, to a network node, UE capability information associated with at least one machine learning component. The UE may receive, from the network node and based on the UE capability information, configuration information corresponding to the at least one machine learning component. The UE may generate a first machine learning output based on the machine learning component. The UE may perform a communication task based on the first machine learning output. Numerous other aspects are described.

Abstract: Aspects described herein relate to receiving, from a network node, a list of supported models or model structures (MS) identifiers (IDs) per machine learning function name (MLFN) or machine learning feature (MLF) at the network node, updating a capability at the UE to an updated capability based on the list of supported models or MS IDs per MLFN or MLF at the network node, and downloading, at the UE and from a model repository, one or more models or MSs per MLFN or MLF based on the updated capability and available resources at the UE. Other aspects relate to transmitting the list of supported models or MS IDs and configuring use of a model or MS ID for a particular MLFN or MLF.

Abstract: Certain aspects of the present disclosure provide techniques for wireless communications by a user equipment (UE). The UE receives a configuration for at least one machine learning function name (MLFN). The UE receives machine learning (ML) data associated with the at least one MLFN. The UE uses the ML data as an input for at least one of: operation or training of an ML model associated with the at least one MLFN.