Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

Abstract: Methods, apparatus, systems, and articles of manufacture to verify integrity of a model are disclosed. An example apparatus includes programmable circuitry to initialize an instance of a trusted execution environment; upload a security manifest of the trusted execution environment and a machine learning model; determine whether to store the machine learning model into a memory based on checking of the security manifest; determine whether the machine learning model is valid; and output a validation result.

Abstract: An example apparatus includes interface circuitry, machine-readable instructions, and at least one processor circuit to be programmed by the machine-readable instructions to access a first set of samples associated with a diffusion model, the first set of samples including a plurality of input data samples, generate a representation of the first set of samples, sample the representation of the first set of samples to generate a representation of a second set of samples, and generate the second set of samples from the representation of the second set of samples, the second set of samples including a plurality of output data samples, an output data sample corresponding to an input data sample and being different from the corresponding input data sample.

Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

Abstract: In one example an apparatus comprises a memory and a processor to create, from a first deep neural network (DNN) model, a first plurality of DNN models, generate a first set of adversarial examples that are misclassified by the first plurality of deep neural network (DNN) models, determine a first set of activation path differentials between the first plurality of adversarial examples, generate, from the first set of activation path differentials, at least one composite adversarial example which incorporates at least one intersecting critical path that is shared between at least two adversarial examples in the first set of adversarial examples, and use the at least one composite adversarial example to generate a set of inputs for a subsequent training iteration of the DNN model. Other examples may be described.

Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

Abstract: Methods, apparatus, systems and articles of manufacture for federated training of a neural network using trusted edge devices are disclosed. An example system includes an aggregator device to aggregate model updates provided by one or more edge devices. The one or more edge devices to implement respective neural networks, and provide the model updates to the aggregator device. At least one of the edge devices to implement the neural network within a trusted execution environment.

Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

Abstract: In one embodiment, an apparatus includes: a bioimpedance sensor to generate bioimpedance information based on bioimpedance sample information from at least some of a plurality of electrodes to be adapted about a portion of a person; at least one biometric sensor to generate biometric information based on biometric sample information from at least some of the plurality of electrodes; at least one environmental sensor to generate environmental context data; and an integration circuit to receive the bioimpedance information, the biometric information and the environmental context data and to adjust the bioimpedance information based at least in part on a value of one or more of the biometric information and the environmental context data. Other embodiments are described and claimed.

Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

Abstract: Various embodiments are generally directed to an apparatus, method, and other techniques to maintain user authentications with common trusted devices. If a user is in possession of a first computing device (e.g., a smartphone), an unlocked state of the first trusted device is maintained if the user is using a nearby trusted device (e.g., a computer) within a certain amount of time. If the first trusted device is in a pocket or other container, a longer span of time is granted to the user to register an on-body state.

Abstract: In one example an apparatus comprises a memory and a processor to create, from a first deep neural network (DNN) model, a first plurality of DNN models, generate a first set of adversarial examples that are misclassified by the first plurality of deep neural network (DNN) models, determine a first set of activation path differentials between the first plurality of adversarial examples, generate, from the first set of activation path differentials, at least one composite adversarial example which incorporates at least one intersecting critical path that is shared between at least two adversarial examples in the first set of adversarial examples, and use the at least one composite adversarial example to generate a set of inputs for a subsequent training iteration of the DNN model. Other examples may be described.

Abstract: Technologies for analyzing a Uniform Resource Locator (URL) include a multi-stage URL analysis system. The multi-stage URL analysis system analyzes the URL using a multi-stage analysis. In the first stage, the multi-stage URL analysis system analyzes the URL using an ensemble lexical analysis. In the second stage, the multi-stage URL analysis system analyzes the URL based on third-party detection results. In the third stage, the multi-stage URL analysis system analyzes the URL based on metadata related to the URL. The multi-stage URL analysis system advances the stages of analysis if a malicious classification score determined by each stage does not satisfy a confidence threshold. The URL may also be selected for additional rigorous analysis using selection criteria not used in by the analysis stages.

Abstract: Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.

Abstract: Methods, apparatus, systems and articles of manufacture for federated training of a neural network using trusted edge devices are disclosed. An example system includes an aggregator device to aggregate model updates provided by one or more edge devices. The one or more edge devices to implement respective neural networks, and provide the model updates to the aggregator device. At least one of the edge devices to implement the neural network within a trusted execution environment.

Abstract: Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

Abstract: Various embodiments are generally directed to an apparatus, method, and other techniques to maintain user authentications with common trusted devices. If a user is in possession of a first computing device (e.g., a smartphone), an unlocked state of the first trusted device is maintained if the user is using a nearby trusted device (e.g., a computer) within a certain amount of time. If the first trusted device is in a pocket or other container, a longer span of time is granted to the user to register an on-body state.

Abstract: In one embodiment, an apparatus includes: a bioimpedance sensor to generate bioimpedance information based on bioimpedance sample information from at least some of a plurality of electrodes to be adapted about a portion of a person; at least one biometric sensor to generate biometric information based on biometric sample information from at least some of the plurality of electrodes; at least one environmental sensor to generate environmental context data; and an integration circuit to receive the bioimpedance information, the biometric information and the environmental context data and to adjust the bioimpedance information based at least in part on a value of one or more of the biometric information and the environmental context data. Other embodiments are described and claimed.