Abstract: An image classification system defends against physically realizable attacks. A training dataset of input images is retrieved and an adversarial image is generated based on one of the input images that is selected. The adversarial image is created by occluding a portion of the selected image by superimposing a predetermined shape (e.g., a rectangle) containing noise on the selected image. A defense against occlusion attacks (DOA) classifier is trained using the training dataset and the adversarial image. The DOA classifier is utilized to classify captured images of items (e.g., street signs) that may have been attacked (e.g., sticker placement, vandalism).

Abstract: A computer-implemented method for identifying root cause failure and fault events is provided. The method includes detecting a trigger point, converting, via an encoder, previous system state data, new batch data in a next system state, and a causal graph to system state-invariant embeddings and system state-dependent embeddings, generating a learned causal graph, via a graph generation layer, by integrating state-invariant and state-dependent information, and predicting, by a prediction layer, future time-series data on the learned causal graph.

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k-1 binary classifiers on top of the semi-supervised representations to obtain k-1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k-1 binary predictions by matching the inconsistent ones to consistent ones of the k-1 binary predictions. The method further includes aggregating the k-1 binary predictions to obtain an ordinal prediction.

Abstract: Methods and systems for evaluating and enhancing a neural network model include constructing a surrogate model that corresponds to a target neural network model, based on a degree of knowledge about the target neural network model. Adversarial attacks against the surrogate model are generated, based on an attack goal, a level of attacker capability, and an attack model. The target neural network model is tested for accuracy under the generated adversarial attacks to determine a degree of robustness of the target neural network. Robustness of the target neural network model is enhanced by replacing facial occlusions in input images before applying the input images to the target neural network.

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k-1 binary classifiers on top of the semi-supervised representations to obtain k-1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k-1 binary predictions by matching the inconsistent ones to consistent ones of the k-1 binary predictions. The method further includes aggregating the k-1 binary predictions to obtain an ordinal prediction.

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k?1 binary classifiers on top of the semi-supervised representations to obtain k?1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k?1 binary predictions by matching the inconsistent ones to consistent ones of the k?1 binary predictions. The method further includes aggregating the k?1 binary predictions to obtain an ordinal prediction.

Abstract: Methods and systems for training a model include determining class prototypes of time series samples from a training dataset. A task corresponding to the time series samples is encoded using the class prototypes and a task-level configuration. A likelihood value is determined based on outputs of a time series density model, a task-class distance from a task embedding model, and a task density model. Parameters of the time series density model, the task embedding model, and the task density model are adjusted responsive to the likelihood value.

Abstract: A computer-implemented method for employing a graph-based adaptive domain generation framework is provided. The method includes, in a training phase, performing domain prototypical network training on source domains, constructing an autoencoding domain relation graph by applying a graph autoencoder to produce domain node embeddings, and performing, via a domain-adaptive classifier, domain-adaptive classifier training to make an informed decision. The method further includes, in a testing phase, given testing samples from a new source domain, computing a prototype by using a pretrained domain prototypical network, inferring node embedding, and making a prediction by the domain-adaptive classifier based on the domain node embeddings.

Abstract: A computer-implemented method for locating root causes is provided. The method includes detecting a trigger point from entity metrics data and key performance indicator (KPI) data, generating a learned causal graph by fusing a state-invariant causal graph with a state-dependent causal graph, and locating the root causes by employing a random walk-based technique to estimate a probability score for each of the entity metrics data by starting from a KPI node.

Abstract: A computer-implemented method for identifying root cause failure and fault events is provided. The method includes detecting a trigger point, converting, via an encoder, previous system state data, new batch data in a next system state, and a causal graph to system state-invariant embeddings and system state-dependent embeddings, generating a learned causal graph, via a graph generation layer, by integrating state-invariant and state-dependent information, and predicting, by a prediction layer, future time-series data on the learned causal graph.

Abstract: A computer-implemented method for detecting trigger points to identify root cause failure and fault events is provided. The method includes collecting, by a monitoring agent, entity metrics data and system key performance indicator (KPI) data, integrating the entity metrics data and the KPI data, constructing an initial system state space, detecting system state changes by calculating a distance between current batch data and an initial state, and dividing a system status into different states.

Abstract: An LDMOS transistor and a method for manufacturing the same are provided. The method includes: forming an epitaxial layer on a substrate, forming a gate structure on an upper surface of the epitaxial layer, forming a body region and a drift region in the epitaxial layer, forming a source region in the body region, forming a first insulating layer on the gate structure and an upper surface of the epitaxial layer and, forming a shield conductor layer on the first insulating layer, forming a second insulating layer covering the shield conductor layer, forming a first conductive path, to connect the source region with the substrate, and forming a drain region in the drift region. By forming the first conductive path which connects the source region with the substrate, the size of the LDMOS transistor and the resistance can be reduced.

Abstract: A computer implemented method is provided. The method includes jointly encoding, by a dual-channel feature extractor, a current time series segment with corresponding static statuses into a compact feature. The method further includes converting, by a binary code extractor, the compact feature into a binary code. The method also includes computing distances between the binary code and all binary codes stored in a binary code database. The method additionally includes retrieving the top relevant multivariate time series segments based on the distances.

Abstract: A computer-implemented method for ordinal prediction is provided. The method includes encoding time series data with a temporal encoder to obtain latent space representations. The method includes optimizing the temporal encoder using semi-supervised learning to distinguish different classes in the labeled space using labeled data, and augment the latent space representations using unlabeled training data, to obtain semi-supervised representations. The method further includes discarding a linear layer after the temporal encoder and fixing the temporal encoder. The method also includes training k?1 binary classifiers on top of the semi-supervised representations to obtain k?1 binary predictions. The method additionally includes identifying and correcting inconsistent ones of the k?1 binary predictions by matching the inconsistent ones to consistent ones of the k?1 binary predictions. The method further includes aggregating the k?1 binary predictions to obtain an ordinal prediction.

Abstract: Methods and systems for training a model include collecting unlabeled training data during operation of a device. A model is adapted to operational conditions of the device using the unlabeled training data. The model includes a shared encoder that is trained on labeled training data from multiple devices and further includes a device-specific decoder that is trained on labeled training data corresponding to the device.

Abstract: A computer-implemented method for ordinal classification of input data is provided. The method includes learning, by an encoder neural network, compact neural representations of the input data. The method further includes freezing the encoder neural network for downstream tasks. The method also includes training, by a hardware processor, K?1 ordinal classifiers on top of the compact neural representations to obtained trained K?1 ordinal classifiers. The method additionally includes generating, by the hardware processor, a predicted ordinal label by aggregating the trained K?1 ordinal classifiers.

Abstract: A method is provided for training a hierarchical graph neural network. The method includes using a time series generated by each of a plurality of nodes to train a graph neural network to generate a causal graph, and identifying interdependent causal networks that depict hierarchical causal links from low-level nodes to high-level nodes to the system key performance indicator (KPI). The method further includes simulating causal relations between entities by aggregating embeddings from neighbors in each layer, and generating output embeddings for entity metrics prediction and between-level aggregation.

Abstract: An LDMOS transistor and a method for manufacturing the same are provided. The method includes: forming an epitaxial layer on a substrate, forming a gate structure on an upper surface of the epitaxial layer, forming a body region and a drift region in the epitaxial layer, forming a source region in the body region, forming a first insulating layer on the gate structure and an upper surface of the epitaxial layer and, forming a shield conductor layer on the first insulating layer, forming a second insulating layer covering the shield conductor layer, forming a first conductive path, to connect the source region with the substrate, and forming a drain region in the drift region. By forming the first conductive path which connects the source region with the substrate, the size of the LDMOS transistor and the resistance can be reduced.

Abstract: An LDMOS transistor and a method for manufacturing the same are provided. The method includes: forming an epitaxial layer on a substrate, forming a gate structure on an upper surface of the epitaxial layer, forming a body region and a drift region in the epitaxial layer, forming a source region in the body region, forming a first insulating layer on the gate structure and an upper surface of the epitaxial layer and, forming a shield conductor layer on the first insulating layer, forming a second insulating layer covering the shield conductor layer, forming a first conductive path, to connect the source region with the substrate, and forming a drain region in the drift region. By forming the first conductive path which connects the source region with the substrate, the size of the LDMOS transistor and the resistance can be reduced.

Abstract: Methods and systems for evaluating and enhancing a neural network model include constructing a surrogate model that corresponds to a target neural network model, based on a degree of knowledge about the target neural network model. Adversarial attacks against the surrogate model are generated, based on an attack goal, a level of attacker capability, and an attack model. The target neural network model is tested for accuracy under the generated adversarial attacks to determine a degree of robustness of the target neural network. Robustness of the target neural network model is enhanced by replacing facial occlusions in input images before applying the input images to the target neural network.