Abstract: A system includes one or more hardware processors, and at least one memory storing instructions that cause the one or more hardware processors to perform operations comprising receiving, from an online platform system, an advertisement opportunity data comprising a plurality of advert opportunities, and a plurality of opportunity timestamps. The operations additionally include receiving, from an advertiser system, advertisement event data comprising a plurality of events and a plurality of event timestamps, and receiving an attribute result of performing a first two-party computation between the advertiser system and the platform system to attribute the plurality of events to the plurality of advert opportunities based on comparing opportunity timestamps and event timestamps, The operations further include deriving an aggregation result that aggregates the events for a subcut of users based on performing a homomorphic encryption, or on performing a non-trusted third party computation.

Abstract: Methods and systems are disclosed for performing private identification matching. The methods and systems store, by a first entity, a first set of private identifiers associated with a first set of data. The methods and systems group, by the first entity, different subsets of the first set of private identifiers into respective buckets of a first plurality of buckets according to a grouping criterion. The methods and systems apply a function to a subset of a second set of data, stored by a second entity, corresponding to private identifiers associated with one or more buckets of a second plurality of buckets, grouped by the second entity, that match private identifiers associated with one or more buckets of the first plurality of buckets. The methods and systems provide, to the first entity, a result of applying the function to the subset of the second set of data.

Abstract: Methods and systems are disclosed for managing access to encrypted data and encryption keys. The system stores, by a key management server, a first encryption key associated with a first service and a second encryption key associated with a second service. The system prevents, by the key management server, the second service from accessing the second encryption key while the first service is performing a first function using the first encryption key and determines that a first threshold period of time associated with the first function has elapsed. The system, in response to determining that the first threshold period of time associated with the first function has elapsed, prevents, by the key management server, the first service from accessing the first encryption key while the second service is performing a second function using the second encryption key.

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: The present disclosure is directed to systems and methods for the selective introduction of low-level pseudo-random noise into at least a portion of the weights used in a neural network model to increase the robustness of the neural network and provide a stochastic transformation defense against perturbation type attacks. Random number generation circuitry provides a plurality of pseudo-random values. Combiner circuitry combines the pseudo-random values with a defined number of least significant bits/digits in at least some of the weights used to provide a neural network model implemented by neural network circuitry. In some instances, selection circuitry selects pseudo-random values for combination with the network weights based on a defined pseudo-random value probability distribution.

Abstract: In some embodiments, an encryption system secures data using a homomorphic encryption. The encryption system encrypts a number by encrypting a number identifier of the number and combining the number and the encrypted number identifier using a mathematical operation to generate an encrypted number. The encrypted numbers may be stored at a server system along with their number identifiers. The server system can then generate an aggregation (e.g., sum) of the encrypted numbers and provide the aggregation, the encrypted numbers, and the number identifiers. The encryption system can then separate the aggregation of the numbers from the aggregation of the encrypted numbers using an inverse of the mathematical operation used in the encryption to effect removal of an aggregation of the encrypted number identifiers of the numbers from the aggregation of the encrypted numbers. The separated aggregation of the numbers is an aggregation of the plurality of the numbers.

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: The present disclosure is directed to systems and methods for the selective introduction of low-level pseudo-random noise into at least a portion of the weights used in a neural network model to increase the robustness of the neural network and provide a stochastic transformation defense against perturbation type attacks. Random number generation circuitry provides a plurality of pseudo-random values. Combiner circuitry combines the pseudo-random values with a defined number of least significant bits/digits in at least some of the weights used to provide a neural network model implemented by neural network circuitry. In some instances, selection circuitry selects pseudo-random values for combination with the network weights based on a defined pseudo-random value probability distribution.

Abstract: In some embodiments, an encryption system secures data using a homomorphic encryption. The encryption system encrypts a number by encrypting a number identifier of the number and combining the number and the encrypted number identifier using a mathematical operation to generate an encrypted number. The encrypted numbers may be stored at a server system along with their number identifiers. The server system can then generate an aggregation (e.g., sum) of the encrypted numbers and provide the aggregation, the encrypted numbers, and the number identifiers. The encryption system can then separate the aggregation of the numbers from the aggregation of the encrypted numbers using an inverse of the mathematical operation used in the encryption to effect removal of an aggregation of the encrypted number identifiers of the numbers from the aggregation of the encrypted numbers. The separated aggregation of the numbers is an aggregation of the plurality of the numbers.