Abstract: A method and system of training an interpretable deep learning model includes receiving an input set of data, which may be complex. The input set of data is provided to deep learning model for feature extraction. In an exemplary embodiment, the deep learning model generates a disentangled latent space of features from the feature extraction. The features may comprise semantically meaningful data which is then provided to a low-complexity learning model. The low-complexity learning model generates output based on a specified task (for example, classification or regression). Being a low-complexity learning model provides confidence that the data output from the deep learning model is inherently interpretable.

Abstract: Techniques for non-iterative federated learning include receiving local models from agents, generating synthetic datasets for the local models, and producing outputs using the local models and the synthetic datasets. A global model is trained based on the synthetic datasets and the outputs.

Abstract: A method for targeted advertisement includes transmitting a pre-filter to the user device, responsive to contextual information from a user device, to determine, using a processor, one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user. The method also includes receiving one or more inferences determined by the pre-filter from the user device and transmitting one or more targeted advertisements to the user device based on one or more inferences.

Abstract: A method for targeted advertisement includes transmitting a pre-filter to the user device, responsive to contextual information from a user device, to determine, using a processor, one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user. The method also includes receiving one or more inferences determined by the pre-filter from the user device and transmitting one or more targeted advertisements to the user device based on one or more inferences.

Abstract: Embodiments of the invention include a computer-implemented method that uses a processor system to access a first machine learning (ML) model. The first ML model has been trained using data of a first server. A first performance metric of the first ML model is determined using data of a second server. A benefit analysis is performed to determine a benefit of the first ML server and the second ML server participating in a federated learning system, where the benefit analysis includes using the first performance metric.

Abstract: An output time-series of a cell of a neural network is captured. A subset of a set of data points of the output time-series is consolidated into a singular data point. The singular data point is fitted in a data representation to form a quantified aggregated data point. The quantified aggregated data point is included in an intermediate time-series. Using the intermediate time-series as an input at an intermediate layer of the neural network, an anonymized output time-series is produced from the neural network.

Abstract: Embodiments of the invention are directed to a computer-implemented method of distributed learning using a fusion-based approach. The method includes determining data statistics at each system node of a plurality of system nodes, wherein each system node respectively comprises an artificial intelligence model. The method further includes determining a set of control and coordination instructions for training each artificial intelligence model at each system node of the plurality of system nodes. The method further includes directing an exchange of data between the plurality of system nodes based on the data statistics of each system node of the plurality of system nodes. The method further includes fusing trained artificial intelligence models from the plurality of system nodes into a fused artificial intelligence model, wherein the trained artificial intelligence models are trained using the set of control and coordination instructions.

Abstract: Second machine learning models trained using respective second data sets can be received. The second machine learning models can be run using a first data set used in training a first machine learning model, where the second machine learning models produce respective outputs. Scores associated with the second machine learning models can be determined by comparing the respective outputs with ground truth associated with the first data set. Based on the scores associated with the second machine learning models, whether the first data set is to be discarded or kept can be determined for training the first machine learning model.

Abstract: Providing an explanation for model outcome can include receiving input data, and passing the input data through an attention-based neural network, where the attention-based neural network learns attention weights associated with contextual embeddings corresponding to tokens of the input data and predicts an outcome corresponding to the input data. Based on an attention weight associated with a contextual embedding corresponding to a token of the input data, a signed relevance score can be determined to associate with the token for quantifying the token's relevance to the outcome. Based on the signed relevance score, an explanation of the token's contribution toward or against the outcome can be provided. The signed relevance score can be computed as a gradient of loss with respect to the attention weight.

Abstract: A first instance of data and a second instance of data can be received, which have been classified differently. The first instance can be input to a first neural network, the first neural network generating a first encoding associated with the first instance. The second instance can be input to a second neural network the second neural network generating a second encoding associated with the second instance. The first neural network and the second neural network form neural network architecture trained to learn similarities in given pair of input objects. Based on the first encoding and the second encoding, a difference can be identified in features of the first instance and the second instance, which contributed to the first instance and the second instance being classified differently.

Abstract: A computer implemented method for analyzing network connections includes identifying a connection of interest and a corresponding set of connection data. The method additionally includes generating one or more saliency maps corresponding to the connection of interest. The method additionally includes mapping the generated one or more saliency maps to underlying protocols and fields, and identifying one or more values corresponding to each of the underlying protocols and fields. The method additionally includes extracting general correspondences from the identified one or more values corresponding to each of the underlying protocols and fields.

Abstract: A method for targeted advertisement includes transmitting a pre-filter to the user device, responsive to contextual information from a user device, to determine, using a processor, one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user. The method also includes receiving one or more inferences determined by the pre-filter from the user device and transmitting one or more targeted advertisements to the user device based on one or more inferences.

Abstract: Method and apparatus for exchanging corpora via a data broker are provided. One example method generally includes receiving, at the data broker from a holder of a first corpus application, a coreset for the first corpus and transmitting the coreset to a set of data providers. The method further includes receiving, from a first data provider of the set of data providers, a value with respect to the coreset of a second corpus associated with the first data provider and transmitting, from the data broker to the holder of the first corpus, the value. The method further includes receiving, at the data broker from the holder of the first corpus, a request to receive the second corpus and receiving the second corpus from the first data provider. The method further includes validating the value of the second corpus and transmitting the second corpus to the holder of the first corpus.

Abstract: A method for targeted advertisement includes transmitting a pre-filter to the user device, responsive to contextual information from a user device, to determine, using a processor, one or more inferences based on physical browsing information, collected at the user device, in compliance with one or more privacy policies of the user. The method also includes receiving one or more inferences determined by the pre-filter from the user device and transmitting one or more targeted advertisements to the user device based on one or more inferences.

Abstract: Neural network protection mechanisms are provided. The neural network protection engine receives a pre-trained neural network computer model and forward propagates a dataset through layers of the pre-trained neural network computer model to compute, for each layer of the pre-trained neural network computer model, inputs and outputs of the layer. For at least one layer of the pre-trained neural network computer model, a differentially private distillation operation is performed on the inputs and outputs of the at least one layer to generate modified operational parameters of the at least one layer. The modified operational parameters of the at least one layer obfuscate aspects of an original training dataset used to train the pre-trained neural network computer model, present in original operational parameters of the at least one layer. The neural network protection engine generates a privatized trained neural network model based on the modified operational parameters.

Abstract: Systems and methods for identifying a device are described. In an example, a processor can receive a first signal having a first waveform encoding data. The processor can extract the data from the first signal. The processor can determine a transformation being used to encode the data in the first waveform. The processor can generate a second signal using the determined transformation to encode the data in a second waveform. The processor can determine a difference between the first waveform and the second waveform. The processor can identify a device as a candidate device that sent the first signal, based on the determined difference.

Abstract: A method of utilizing a computing device to correct source data used in machine learning includes receiving, by the computing device, first data. The computing device corrects the source data via an application of a covariate shift to the source data based upon the first data where the covariate shift re-weighs the source data.

Abstract: Techniques for performing root cause analysis in dynamic software testing via probabilistic modeling are provided. In one example, a computer-implemented method includes initializing, by a system operatively coupled to a processor, a threshold value, a defined probability value, and a counter value. The computer-implemented method also includes, in response to determining, by the system, that a probability value assigned to a candidate payload of one or more candidate payloads exceeds the defined probability value, and in response to determining, by the system, that the counter value exceeds the threshold value: determining, by the system, that a match exists between the candidate payload and an input point based on an application of the candidate payload to the input point resulting in a defined condition, wherein the one or more candidate payloads are represented by population data accessed by the system.

Abstract: Generating an environment information map from a wireless communication system having directional communication capabilities. A plurality of features are extracted and logged resultant from a communication link attempt at multiple beam directions and training at least one machine learning model based on the plurality of extracted features from the first beam direction and the at least one additional beam directions to infer an environment information map of the area between the first transmitter and the receiver.

Abstract: A method and system of training an interpretable deep learning model includes receiving an input set of data, which may be complex. The input set of data is provided to deep learning model for feature extraction. In an exemplary embodiment, the deep learning model generates a disentangled latent space of features from the feature extraction. The features may comprise semantically meaningful data which is then provided to a low-complexity learning model. The low-complexity learning model generates output based on a specified task (for example, classification or regression). Being a low-complexity learning model provides confidence that the data output from the deep learning model is inherently interpretable.