Intel Corporation

Hiddenlayer, Inc.

Apple Inc.

Ravikumar Balakrishnan

Srikathyayani Srikanteswara

Venkatesan Nallampatti Ekambaram

Nageen Himayat

Maruti Gupta Hyde

Rath Vannithamby

Gabriel Arrobo Vidal

Shahrnaz Azizi

Satish Chandra Jha

S M Iftekharul Alam

Thomas J Kenney

Laurent Cariou

Alexander W Min

Vallabhajosyula S Somayazulu

Yi Zhang

Arjun Anand

Ned M Smith

Kathiravetpillai Sivanesan

Zongrui Ding

Javier Perez-Ramirez

Eve M Schooler

Kuilin Clark Chen

Mustafa Akdeniz

Stepan Karpenko

Ariela Zeira

Mohammad Mamunur Rashid

Jason Martin

Sebastian Schoenberg

Vesh Raj Sharma Banjade

Yiting Liao

Roya Doostnejad

Moreno Ambrosin

Jessica C McCarthy

Maria E Ramirez Loaiza

Sagar Dhakal

Ajay Gupta

Qinghua Li

Carlos Cordeiro

Francesc Guim Bernat

Robert J Stacey

Po-Kai Huang

Kshitij Arun Doshi

Xiaogang Chen

Muthaiah Venkatachalam

Rajesh Poornachandran

Feng Jiang

Christian Maciocco

Giuseppe Beppe Raffa

Ignacio Javier Alvarez

Hassnaa Moustafa

Daniel F Bravo

Dave A Cavalcanti

Farid Adrangi

Xiangying Yang

Feng Xue

Alexander Bachmutsky

Vijay Sarathi Kesavan

Andrew Davis

Juan Fang

Jeffrey Sedayao

Mikhail T Galeev

Nir Yizhak Balaban

Marcin Spoczynski

Mi Sun Park

Navid Naderializadeh

Ashraf H Wadaa

Leor Rom

Venkateshan Udhayan

Amar Srivastava

Nesreen K Ahmed

Hesham Mostafa

Mark R Eisen

Jacob Winick

Zeliang Kan

Hengrui Jia

Srikathyayani Skikanteswara

Vallahajosyula S Somayazulu

Klaus Schneider

Techniques for assessing multi-modal inputs to a machine learning model involve receiving a multimodal input containing an image, producing several transformed versions of that image, and generating embeddings for both the original and transformed images. A pairwise similarity analysis among all embeddings is conducted to determine distance values. Two dissimilarity metrics can then be calculated: one reflecting the differences among the transformed images, and another comparing the original image to its transformed versions. If the dissimilarity among the transformed images is greater than that between the original and transformed images plus a threshold, the system triggers a remediation action. This action either blocks the input from being processed by the machine learning model or prevents the model's output from being returned to the requester, thereby enhancing the reliability and security of the model.

Multimodal AI model protection using embeddings

An apparatus of a transmitter computing node n (TX node n) of a wireless network, one or more computer readable media, a system, and a method. The apparatus includes one or more processors to: implement machine learning (ML) based training rounds, each training round including: determining a local action value function Q(h, a; θ) corresponding to a value of performing a radio resource management (RRM) action aat a receiving computing node n (RX node n) associated with TX node n using policy parameter θand based on h, hincluding channel state information at RX node n; and determining, based on an overall action value function Qat time t, an estimated gradient of an overall loss at time t for overall policy parameter θ(∇L(θ)), wherein Qcorresponds to a mixing of local action value functions Q(h, a; θ) for all TX nodes i in the network at time t including TX node n; and determine, in response to a determination that ∇L(θ) is close to zero for various values of t during training, a trained local action value function Qto generate a trained action value relating to data communication between TX node n and RX node n.

Apparatus, system, method and computer-implemented storage media to implement radio resource management policies using machine learning

Systems and techniques for cross-layer automated fault tracking and anomaly detection are described herein. Anomaly data may be obtained from a plurality of layers of a network. Elements of the anomaly data may be identified that correspond to a data flow of an application executing on the network. An artificial intelligence model may be trained using the elements of the anomaly data to generate an impact score for the application. The impact score may be generated for the application by evaluating current network metrics using the artificial intelligence model. An operational component of the network may be modified based on the impact score.

Cross-layer automated fault tracking and anomaly detection

A plurality of queries are input into an artificial intelligence (AI) model. The AI model is made up of a plurality of layers including an input layer, an output layer, and at least one intermediate layer between the input layer and the output layer. Each intermediate layer, during inference, can output a plurality of activations. Thereafter, for each query, activations are intercepted from at least one of the intermediate layers. It is then determined whether a distribution of the intercepted activations across the queries indicates that the queries seek to cause the AI model to behave in an undesired manner by conducting a distance-based similarity analysis between the intercepted activations and reference activations. Data characterizing such determination is then provided to a consuming application or process. Related apparatus, systems, techniques and articles are also described.

Detection of privacy attacks on machine learning models

In one embodiment, an apparatus of an access point (AP) node of a network includes an interconnect interface to connect the apparatus to one or more components of the AP node and a processor to: access scheduling requests from a plurality of devices, select a subset of the devices for scheduling of resource blocks in a time slot, and schedule wireless resource blocks in the time slot for the subset of devices using a neural network (NN) trained via deep reinforcement learning (DRL).

Model-assisted deep reinforcement learning based scheduling in wireless networks

An apparatus of an edge computing node, a method, and a machine-readable storage medium. The apparatus is to decode messages from a plurality of clients within the edge computing network, the messages including respective coded data for respective ones of the plurality of clients; computing estimates of metrics related to a global model for federated learning using the coded data, the metrics including a gradient on the coded data; use the metrics to update the global model to generate an updated global model, wherein the edge computing node is to update the global model by calculating the gradient on the coded data based on a linear fit of the global model to estimated labels from the federated learning; and send a message including the updated global model for transmission to at least some of the clients.

Uses of coded data at multi-access edge computing server

A method of implementing distributed AI or ML learning for autonomous vehicles is disclosed. An AI or ML model specific to a location or a type of the location is generated at a vehicle. In response to a detection that the vehicle is within a proximity to a road side unit (RSU) associated with the location or the type of the location or the vehicle is within a proximity to an additional vehicle that is present or anticipated to be present at the location or the type of the location, causing an AI or ML model transmission to the additional vehicle or the RSU. Based on the causing the AI or ML model reception, causing deployment of an additional AI or ML model in the vehicle to optimize the vehicle for the location or the type of the location.

Distributed learning to learn context-specific driving patterns

Methods, systems, and computer programs are presented for implementing Personalized Mobility as a Service (PMaaS) to improve transportation services delivery. One storage medium includes instructions for detecting, by a mobility as a service (MaaS) system, a request for a trip from a user device of a user. The storage medium further includes instructions for mapping, using a model executing on the machine, the user to a persona from a plurality of persona models. Each persona model has one or more characteristics associated with users of the MaaS system. Further yet, the storage medium includes instructions for determining trip parameters for the trip based on the persona mapped to the user, the trip parameters defining one or more trip segments for the trip, and instructions for providing trip parameters to the user device.

Personalized mobility as a service

A method can be performed by a first node for determining a parameter of physical (PHY) layer circuitry of a second node. The method can include implementing a cascaded hierarchy of techniques to determine, based on an electrical signal from a second node, a parameter of the PHY layer circuitry of the second node, and causing an antenna of the first node to transmit an electromagnetic wave consistent with the determined parameter.

Feature detection in collaborative radio networks

Methods, apparatus, systems, and articles of manufacture are disclosed that coordinate network traffic between a wireless network device and a computing platform. An example apparatus includes a wake-up selector to generate a target wait time parameter based on a workload type of a number of packets obtained from a network device and a user preference, the target wait time parameter indicative of a time interval that, when met, causes a modem to retrieve the number of packets, a data frame generator to generate a data frame that causes the network device to buffer the number of packets for the time interval, and a network packet controller to negotiate, using the data frame, the target wait time parameter with a network device.

Methods and apparatus for coordination of network traffic between wireless network devices and computing platforms

Methods, apparatus, systems, and articles of manufacture are disclosed that generate dynamic latency values. An example apparatus includes an active status controller to determine that a modem is active based on a number of packets obtained from a network, a prediction controller to predict that the number of packets are indicative of a workload type based on a trained model, and a latency value generator to generate a latency value based on the workload type of the number of packets, the latency value to cause a processor processing the number of packets to enter a power saving state or a power executing state.

Methods and apparatus to generate dynamic latency messages in a computing system

System and techniques for information centric network (ICN) protocol for federated learning are described herein. An interest packet may be received on a first interface to start a federated learning round. Here, the interest packet includes a participant criterion and a federated learning round expiration. An entry, that includes the federated learning round expiration, is created in a pending interest table (PIT) for the interest packet. The interest packet is forwarded, in accordance with a forwarding information base (FIB), to a set of interfaces before the federated learning round expiration. When a data packet from a node, that meeting the participant criterion, is received in response to the interest packet, the data packet is forwarded on the first interface in accordance with the PIT entry.

Information centric network protocol for federated learning

Systems and techniques for information centric network (ICN) interworking are described herein. For example, a request may be received at a convergence layer of a node. Here, the request originates from an application on the node. A network protocol, from several available to the node, may be determined to transmit the request. The node then transmits the request via the selected network protocol.

Information centric network interworking techniques

Systems and methods of using machine-learning to improve communications across different networks are described. A CIRN node identifies whether it is within range of a source and destination node in a different network using explicit information or a machine-learning classification model. A neural network is trained to avoid interference using rewards associated with reduced interference or retransmission levels in each network or improved throughput at the CIRN node. A machine-learning scheduling algorithm determines a relay mode of the CIRN node for source and destination node transmissions. The scheduling algorithm is based on the probability of successful transmission between the source and destination nodes multiplied by a collaboration score for successful transmission and the probability of unsuccessful transmission of the particular packet multiplied by a collaboration score for unsuccessful transmission.

System and method using collaborative learning of interference environment and network topology for autonomous spectrum sharing

Systems and techniques for information-centric network namespace policy-based content delivery are described herein. A registration request may be received from a node on an information-centric network (ICN). Credentials of the node may be validated. The node may be registered with the ICN based on results of the validation. A set of content items associated with the node may be registered with the ICN. An interest packet may be received from a consumer node for a content item of the set of content items that includes an interest packet security level for the content item. Compliance of the security level of the node with the interest packet security level may be determined. The content item may be transmitted to the consumer node.

Information-centric network namespace policy-based content delivery

Growing community of inventors

Hillsboro, OR, United States of America

Ravikumar Balakrishnan