Abstract: Techniques are disclosed for detecting adversarial attacks. A machine learning (ML) system processes the input into and output of a ML model using an adversarial detection module that does not include a direct external interface. The adversarial detection module includes a detection model that generates a score indicative of whether the input is adversarial using, e.g., a neural fingerprinting technique or a comparison of features extracted by a surrogate ML model to an expected feature distribution for the output of the ML model. In turn, the adversarial score is compared to a predefined threshold for raising an adversarial flag. Appropriate remedial measures, such as notifying a user, may be taken when the adversarial score satisfies the threshold and raises the adversarial flag.

Abstract: Mechanisms and methods are provided for establishing vectors indicating the presence, in a first vehicle and second vehicle, of a super-set of vehicle features present across a fleet of vehicles. The first vehicle may be a reference vehicle. A distance function of the vectors may be calculated in order to establish a similarity score indicating the degree of similarity between the designs of the two vehicles. If the second vehicle is sufficiently similar to the reference vehicle, a software update may be recommended and applied.

Abstract: An access system for a vehicle may include at least one antenna configured to receive access signals for authorization to gain access to the vehicle, and a controller configured to receive motion data from a key fob associated with the vehicle, the motion data indicative of a route of a user associated with the key fob, classify the motion data as one of an open route and a closed route, and restrict access to the vehicle in response to the motion data being classified as an open route.

Abstract: Examples are disclosed for methods and mechanisms to address Base Transceiver Stations (BTSes) attempting to hijack Mobile Stations (MSes) in wireless communication networks. In some example methods, a record having values for a set of features associated with an MS and a BTS of a wireless communication net may be processed. A score for the record may be calculated, for example based on a machine-learning model pertaining to the set of features, and a determination may be made as to whether the record demonstrates an anomalous condition based upon the score. The set of features may include at least one feature based on a measured power of the BTS.

Abstract: Techniques for detecting anomalies or cyber attacks on a vehicle. A computer-implemented method for anomaly or attack detection includes determining, using a first model, a first predicted value of a first variable message associated with a vehicle, determining, using a second model, a second predicted value of the first variable message associated with the vehicle, determining, based on a difference between an actual value of the first variable message and the first predicted value of the first variable message and on a difference between the actual value of the first variable message and the second predicted value of the first variable message, a vector, and determining, using a third model, an output value based on the vector, the output value corresponding to at least one of a likelihood that an anomaly or an attack is occurring or a type of the anomaly or the attack.

Abstract: Mechanisms and methods are provided for establishing vectors indicating the presence, in a first vehicle and second vehicle, of a super-set of vehicle features present across a fleet of vehicles. The first vehicle may be a reference vehicle. A distance function of the vectors may be calculated in order to establish a similarity score indicating the degree of similarity between the designs of the two vehicles. If the second vehicle is sufficiently similar to the reference vehicle, a software update may be recommended and applied.

Abstract: Techniques are disclosed for detecting adversarial attacks. A machine learning (ML) system processes the input into and output of a ML model using an adversarial detection module that does not include a direct external interface. The adversarial detection module includes a detection model that generates a score indicative of whether the input is adversarial using, e.g., a neural fingerprinting technique or a comparison of features extracted by a surrogate ML model to an expected feature distribution for the output of the ML model. In turn, the adversarial score is compared to a predefined threshold for raising an adversarial flag. Appropriate remedial measures, such as notifying a user, may be taken when the adversarial score satisfies the threshold and raises the adversarial flag.

Abstract: A method for inspecting data to determine a charging treatment is described. The method comprises receiving, from a user equipment, first data including a request for content and sending, to a content provider system, the first data including the request for content. The method comprises receiving, from the content provider system, second data including the requested content. The method comprises inspecting the first data or the second data to determine a charging treatment for the requested content. The method comprises sending, to the user equipment, the second data including the requested content while applying the charging treatment to the requested content.

Abstract: A method, system and apparatus are described, the method, system, and apparatus, in one embodiment including assigning at a processor an initial driving score S(V) to a vehicle which is being driven, receiving a report at a communication system controlled by the processor, the report including a report of a reckless driving incident in a vicinity of a receiver disposed in the vehicle, incrementing S(V) by the processor upon receipt of the report of the reckless driving incident, decreasing S(V) by the processor for every unit of driving the vehicle is driven, broadcasting the value of S(V) to other vehicles by the communication system controlled by the processor. Related methods, systems and apparatuses are also described.

Abstract: A method, system and apparatus are described, the method, system, and apparatus, in one embodiment including assigning at a processor an initial driving score S(V) to a vehicle which is being driven, receiving a report at a communication system controlled by the processor, the report including a report of a reckless driving incident in a vicinity of a receiver disposed in the vehicle, incrementing S(V) by the processor upon receipt of the report of the reckless driving incident, decreasing S(V) by the processor for every unit of driving the vehicle is driven, broadcasting the value of S(V) to other vehicles by the communication system controlled by the processor. Related methods, systems and apparatuses are also described.