Abstract: A computer-implemented method for training a machine-learning network, wherein the network includes receiving an input data from a sensor, wherein the input data includes data indicative of an image, wherein the sensor includes a video, radar, LiDAR, sound, sonar, ultrasonic, motion, or thermal imaging sensor, generating an adversarial version of the input data utilizing an optimizer, wherein the adversarial version of the input data utilizes a subset of the input data, parameters associated with the optimizer, and one or more perturbation tiles, determining loss function value in response to the adversarial version of the input data and a classification of the adversarial version of the input data, determining a perturbation tile in response the loss function value associated with one or more subsets of the adversarial version of the input data, and output a perturbation that includes at least the perturbation tile.

Abstract: A system for training a machine learning model using a batch based active learning approach. The system includes an information source and an electronic processor. The electronic processor is configured to receive a machine learning model to train, an unlabeled training data set, a labeled training data set, and an identifier of the information source. The electronic processor is also configured to select a batch of training examples from the unlabeled training data set and send, to the information source, a request for, for each training example included in the batch, a label for the training example. The electronic processor is further configured to, for each training example included in the batch, receive a label, associate the training example with the label, and add the training example to the labeled training data set. The electronic processor is also configured to train the machine learning model using the labeled training data.

Abstract: A computer-program product storing instructions which, when executed by a computer, cause the computer to receive an input data from a sensor, wherein the input data includes data indicative of an image, wherein the sensor includes a video, radar, LiDAR, sound, sonar, ultrasonic, motion, or thermal imaging sensor, generate an adversarial version of the input data, utilizing a generator, in response to the input data, create a training data set utilizing the input data and the adversarial version of the input data, determine an update direction of a meta model utilizing stochastic gradient respect with respect to an adversarial loss, and determine a cross-entropy based classification loss in response to the input data and classification utilizing a classifier, and update the meta model and the classifier in response to the cross-entropy classification loss utilizing the training data set.

Abstract: A computer-implemented method includes applying a filter to input data based on an initial set of parameters to generate an initial feature map. The filter is configured to activate a filter function that involves a periodic function. The method includes performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform. The method includes applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map. The method includes performing a multiplicative operation on the first linear transform and the first feature map to generate a first product. The method includes performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform. The method includes generating output data that takes into account at least the second linear transform.

Abstract: Performing an adversarial attack on a neural network classifier is described. A dataset of input-output pairs is constructed, each input element of the input-output pairs randomly chosen from a search space, each output element of the input-output pairs indicating a prediction output of the neural network classifier for the corresponding input element. A Gaussian process is utilized on the dataset of input-output pairs to optimize an acquisition function to find a best perturbation input element from the dataset. The best perturbation input element is upsampled to generate an upsampled best input element. The upsampled best input element is added to an original input to generate a candidate input. The neural network classifier is queried to determine a classifier prediction for the candidate input. A score for the classifier prediction is computed. The candidate input is accepted as a successful adversarial attack responsive to the classifier prediction being incorrect.

Abstract: A system for training a neural work that includes an input interface for accessing input data for the neural network and a processor in communication with the input interface. The processor is programmed to receive input at the neural network and output a trained neural networking utilizing a forward prorogation and a backward propagation, wherein the forward propagation includes utilizing a root-finding procedure to identify a fixed point associated with one or more parameters of the neural network, wherein the backward propagation includes identifying a derivative of a loss associated with the parameters of the network.

Abstract: Markov random field parameters are identified to use for covariance modeling of correlation between gradient terms of a loss function of the classifier. A subset of images are sampled, from a dataset of images, according to a normal distribution to estimate the gradient terms. Black-box gradient estimation is used to infer values of the parameters of the Markov random field according to the sampling. Fourier basis vectors are generated from the inferred values. An original image is perturbed using the Fourier basis vectors to obtain loss function values. An estimate of a gradient is obtained from the loss function values. An image perturbation is created using the estimated gradient. The image perturbation is added to an original input to generate a candidate adversarial input that maximizes loss in identifying the image by the classifier. The neural network classifier is queried to determine a classifier prediction for the candidate adversarial input.

Abstract: A computer-implemented method for training a machine-learning network, wherein the network includes receiving an input data from a sensor, wherein the input data includes data indicative of an image, wherein the sensor includes a video, radar, LiDAR, sound, sonar, ultrasonic, motion, or thermal imaging sensor, generating an adversarial version of the input data utilizing an optimizer, wherein the adversarial version of the input data utilizes a subset of the input data, parameters associated with the optimizer, and one or more perturbation tiles, determining loss function value in response to the adversarial version of the input data and a classification of the adversarial version of the input data, determining a perturbation tile in response the loss function value associated with one or more subsets of the adversarial version of the input data, and output a perturbation that includes at least the perturbation tile.

Abstract: A computer-program product storing instructions which, when executed by a computer, cause the computer to receive an input data from a sensor, wherein the input data includes data indicative of an image, wherein the sensor includes a video, radar, LiDAR, sound, sonar, ultrasonic, motion, or thermal imaging sensor, generate an adversarial version of the input data, utilizing a generator, in response to the input data, create a training data set utilizing the input data and the adversarial version of the input data, determine an update direction of a meta model utilizing stochastic gradient respect with respect to an adversarial loss, and determine a cross-entropy based classification loss in response to the input data and classification utilizing a classifier, and update the meta model and the classifier in response to the cross-entropy classification loss utilizing the training data set.

Abstract: A computer-implemented method includes applying a filter to input data based on an initial set of parameters to generate an initial feature map. The filter is configured to activate a filter function that involves a periodic function. The method includes performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform. The method includes applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map. The method includes performing a multiplicative operation on the first linear transform and the first feature map to generate a first product. The method includes performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform. The method includes generating output data that takes into account at least the second linear transform.

Abstract: A system for training a neural work that includes an input interface for accessing input data for the neural network and a processor in communication with the input interface. The processor is programmed to receive input at the neural network and output a trained neural networking utilizing a forward prorogation and a backward propagation, wherein the forward propagation includes utilizing a root-finding procedure to identify a fixed point associated with one or more parameters of the neural network, wherein the backward propagation includes identifying a derivative of a loss associated with the parameters of the network.

Abstract: Performing an adversarial attack on a neural network classifier is described. A dataset of input-output pairs is constructed, each input element of the input-output pairs randomly chosen from a search space, each output element of the input-output pairs indicating a prediction output of the neural network classifier for the corresponding input element. A Gaussian process is utilized on the dataset of input-output pairs to optimize an acquisition function to find a best perturbation input element from the dataset. The best perturbation input element is upsampled to generate an upsampled best input element. The upsampled best input element is added to an original input to generate a candidate input. The neural network classifier is queried to determine a classifier prediction for the candidate input. A score for the classifier prediction is computed. The candidate input is accepted as a successful adversarial attack responsive to the classifier prediction being incorrect.

Abstract: Markov random field parameters are identified to use for covariance modeling of correlation between gradient terms of a loss function of the classifier. A subset of images are sampled, from a dataset of images, according to a normal distribution to estimate the gradient terms. Black-box gradient estimation is used to infer values of the parameters of the Markov random field according to the sampling. Fourier basis vectors are generated from the inferred values. An original image is perturbed using the Fourier basis vectors to obtain loss function values. An estimate of a gradient is obtained from the loss function values. An image perturbation is created using the estimated gradient. The image perturbation is added to an original input to generate a candidate adversarial input that maximizes loss in identifying the image by the classifier. The neural network classifier is queried to determine a classifier prediction for the candidate adversarial input.

Abstract: A system for training a machine learning model using a batch based active learning approach. The system includes an information source and an electronic processor. The electronic processor is configured to receive a machine learning model to train, an unlabeled training data set, a labeled training data set, and an identifier of the information source. The electronic processor is also configured to select a batch of training examples from the unlabeled training data set and send, to the information source, a request for, for each training example included in the batch, a label for the training example. The electronic processor is further configured to, for each training example included in the batch, receive a label, associate the training example with the label, and add the training example to the labeled training data set. The electronic processor is also configured to train the machine learning model using the labeled training data.