Abstract: Techniques for sanitization of machine learning (ML) models are provided. A first ML model is received, along with clean training data. A path is trained between the first ML model and a second ML model using the clean training data. A sanitized ML model is generated based on at least one point on the trained path. One or more ML functionalities are then facilitated using the sanitized ML model.

Abstract: In an embodiment, a method for generating contrastive information for a classifier prediction comprises receiving image data representative of an input image, using a deep learning classifier model to predict a first classification for the input image, evaluating the input image using a plurality of classifier functions corresponding to respective high-level features to identify one or more of the high-level features absent from the input image, and identifying, from among the high-level features absent from the input image, a pertinent-negative feature that, if added to the input image, will result in the deep learning classifier model predicting a second classification for the modified input image, the second classification being different from the first classification. In an embodiment, the method includes creating a pertinent-positive image that is a modified version of the input image that has the first classification and fewer than all superpixels of the input image.

Abstract: Methods and systems for explainable machine learning are described. In an example, a processor can receive a data set from a plurality of data sources corresponding to a plurality of domains. The processor can train a machine learning model to learn a plurality of vectors that indicate impact of the plurality of domains on a plurality of assets. The machine learning model can be operable to generate forecasts relating to performance metrics of the plurality of assets based on the plurality of vectors. In some examples, the machine learning model can be a neural attention network with shared hidden layers.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate computational creativity are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a learner component that learns mappings of data features from a feature space to a creativity attribute of a model to define a creativity control function of the model. The computer executable components can further comprise a generator component that employs the model to generate a creative data sample based on the creativity control function.

Abstract: A method for securing an IT (information technology) system using a set of methods for knowledge extraction, event detection, risk estimation and explanation for ranking cyber-alerts which includes a method to explain the relationship (or an attack pathway) from an entity (user or host) and an event context to another entity (a high-value resource) and an event context (attack or service failure).

Abstract: A black box optimization method, system, and computer program product include implementing an average gradient estimator using a forward difference of function values at multiple random directions, performing variance reduction via gradient blending with an output of the average gradient estimator using a control variate, and performing binary quantization of a result of the variance reduction.

Abstract: A certification method, system, and computer program product include certifying an adversarial robustness of a convolutional neural network by deriving an analytic solution for a neural network output using an efficient upper bound and an efficient lower bound on an activation function and applying the analytic solution in computing a certified robustness.

Abstract: An adversarial robustness testing method, system, and computer program product include testing a robustness of a black-box system under different access settings via an accelerator.

Abstract: A processor receives input data and provides the input data to a first neural network including a first neural network model. The first neural network model has a first numerical precision level. A first feature vector is generated from the input data using the first neural network. The input data is provided to a second neural network including a second neural network model. The second neural network model has a second numerical precision level different from the first numerical precession level. A second feature vector is generated from the input data using the second neural network. A difference metric is computed between the first feature vector and the second feature vector. The difference metric is indicative of whether the input data includes adversarial data.

Abstract: A method, system, and computer program product, including generating a contrastive explanation for a decision of a classifier trained on structured data, highlighting an important feature that justifies the decision, and determining a minimal set of new values for features that alter the decision.

Abstract: A method, system, and computer program product, including highlighting a minimally sufficient component in an input to justify a classification, identifying contrastive characteristics or features that are minimally and critically absent, maintaining the classification and distinguishing it from a second input that is closest to the classification but is identified as a second classification.

Abstract: An electronic device is provided, including a housing, a front cover, a display panel module, a conductive structure, a circuit board, and an IC element, wherein the front cover is disposed on a front side of the electronic device and coupled to the housing. The conductive structure is disposed on the front cover and located outside an active display region of the display panel module. The IC element is disposed on the circuit board and electrically coupled to the conductive structure. When a human body is approaching to the front cover, the conductive structure generates an electrical signal to the IC element.

Abstract: A computer implemented method and system of presenting content on a display of a computing device is provided. Historical data including data of a plurality of customers and data of a plurality of products is received. A hybrid graph is created. The hybrid graph includes one or more customer nodes and product nodes. Between each two customers, a customer weight factor is applied. Between each two products, a product weight factor is applied. One or more products related to a seed product are identified. For each identified related product, a return affinity score towards the requestor customer is determined. A representation of the related products is sent to be displayed on the computing device of the requestor customer, based on the affinity score.

Abstract: An inductor structure with height limit, which comprises: a conductor formed in a bent shape, and is set with a plurality of bending-portions, wherein a first connecting-pin and a second connecting-pin are respectively set at two ends of the conductor; a first magnetic core set with a first combining-surface, wherein the first combining-surface forms a concave groove to accommodate the conductor; and a second magnetic core set with a second combining-surface, wherein the second combining-surface forms a second concave groove to accommodate the conductor; wherein the second combining-surface is combined on the first combining-surface; wherein the conductor is sheathed and set between the first magnetic core and the second magnetic core, and is set with the first connecting-pin and the second connecting-pin exposedly. Therefore, the present invention can increase the magnetic (coupling) route length under the height limit to produce an effect of increasing the inductance value and current.

Abstract: An optical fingerprint sensing module attached to a base is provided. The base includes a first surface, a second surface and an opening extending through the first surface and the second surface. The optical fingerprint sensing module includes a fixing frame and a sensor integrated circuit (IC). The fixing frame is disposed in the opening of the base. The sensor IC is disposed in a receiving groove of the fixing frame and includes a plurality of photo sensors. The photo sensors receive light reflected from a user's finger through the opening of the base.

Abstract: The large-current inductor includes a first core member having a first winding piece, a second winding piece, a first indentation, and a second indentation; a second core member having a third winding piece, a fourth winding piece, a third indentation, and a fourth indentation; a third core member attached and joined to first lateral sides of the first and second core members; and a fourth core member attached and joined to second lateral sides of the first and second core members. A first coil member winds around the first and third winding pieces, and has its ends embedded into the first and third indentations. A second coil member winds around the second and fourth winding pieces, and has its ends embedded into the second and fourth indentations. The inductor enhances efficiency of energy storage by mutual inductance, and limits large current flow by leakage inductance.

Abstract: A method and system of analyzing a symbolic sequence is provided. Metadata of a symbolic sequence is received from a computing device of an owner. A set of R random sequences are generated based on the received metadata and sent to the computing device of the owner of the symbolic sequence for computation of a feature matrix based on the set of R random sequences and the symbolic sequence. The feature matrix is received from the computing device of the owner. Upon determining that an inner product of the feature matrix is below a threshold accuracy, the iterative process returns to generating R random sequences. Upon determining that the inner product of the feature matrix is at or above the threshold accuracy, the feature matrix is categorized based on machine learning. The categorized global feature matrix is sent to be displayed on a user interface of the computing device of the owner.

Abstract: Techniques that facilitate graph similarity analytics are provided. In one example, a system includes an information component and a similarity component. The information component generates a first information index indicative of a first entropy measure for a first graph-structured dataset associated with a machine learning system. The information component also generates a second information index indicative of a second entropy measure for a second graph-structured dataset associated with the machine learning system. The similarity component determines similarity between the first graph-structured dataset and the second graph-structured dataset based on a graph similarity computation associated with the first information index and the second information index.

Abstract: The large-current inductor includes a first core member having a first winding piece, a second winding piece, a first indentation, and a second indentation; a second core member having a third winding piece, a fourth winding piece, a third indentation, and a fourth indentation; a third core member attached and joined to first lateral sides of the first and second core members; and a fourth core member attached and joined to second lateral sides of the first and second core members. A first coil member winds around the first and third winding pieces, and has its ends embedded into the first and third indentations. A second coil member winds around the second and fourth winding pieces, and has its ends embedded into the second and fourth indentations. The inductor enhances efficiency of energy storage by mutual inductance, and limits large current flow by leakage inductance.

Abstract: The multiple winding inductor assembly includes a first core piece, a second core piece, a first conductor, and a first core assembly. The first core assembly includes a third core piece and a second conductor. The first and second conductors, together with the first, second, and third core pieces, form multiple inductors that, when working individually, do not cause mutual inductance on those not at work, thereby avoiding energy consumption. In addition, the inductor assembly may be extended in only one direction when cascading more inductors, facilitating circuit design and layout, and the configuration of the inductor assembly on the circuit board.