International Business Machines Corporation

Heqing Huang

Zhongshu Gu

Jialong Zhang

Ian M Molloy

Dimitrios Pendarakis

Suresh N Chari

Taesung Lee

Xiaokui Shu

Dong Su

Marc Philippe Stoecklin

Jiyong Jang

Josyula R Rao

Kapil Kumar Singh

Dhilung Hang Kirat

Youngja Park

Benjamin J Edwards

Benjamin E Andow

Marc Phillipe Stoecklin

Using a deep learning inference system, respective similarities are measured for each of a set of intermediate representations to input information used as an input to the deep learning inference system. The deep learning inference system includes multiple layers, each layer producing one or more associated intermediate representations. Selection is made of a subset of the set of intermediate representations that are most similar to the input information. Using the selected subset of intermediate representations, a partitioning point is determined in the multiple layers used to partition the multiple layers into two partitions defined so that information leakage for the two partitions will meet a privacy parameter when a first of the two partitions is prevented from leaking information. The partitioning point is output for use in partitioning the multiple layers of the deep learning inference system into the two partitions.

System for measuring information leakage of deep learning models

Deep learning training service framework mechanisms are provided. The mechanisms receive encrypted training datasets for training a deep learning model, execute a FrontNet subnet model of the deep learning model in a trusted execution environment, and execute a BackNet subnet model of the deep learning model external to the trusted execution environment. The mechanisms decrypt, within the trusted execution environment, the encrypted training datasets and train the FrontNet subnet model and BackNet subnet model of the deep learning model based on the decrypted training datasets. The FrontNet subnet model is trained within the trusted execution environment and provides intermediate representations to the BackNet subnet model which is trained external to the trusted execution environment using the intermediate representations. The mechanisms release a trained deep learning model comprising a trained FrontNet subnet model and a trained BackNet subnet model, to the one or more client computing devices.

Verifiable deep learning training service

Mechanisms are provided for detecting abnormal system call sequences in a monitored computing environment. The mechanisms receive, from a computing system resource of the monitored computing environment, a system call of an observed system call sequence for evaluation. A trained recurrent neural network (RNN), trained to predict system call sequences, processes the system call to generate a prediction of a subsequent system call in a predicted system call sequence. Abnormal call sequence logic compares the subsequent system call in the predicted system call sequence to an observed system call in the observed system call sequence and identifies a difference between the predicted system call sequence and the observed system call sequence based on results of the comparing. The abnormal call sequence logic generates an alert notification in response to identifying the difference.

Recurrent neural network based anomaly detection

An approach is provided that identifies Internet of Things (IoT) network anomalies. The approach receives IoT endpoint device data at an attestation entity included in the network. The data is logged to a secured ledger and analyzed. Conditions pertaining to the IoT endpoint devices are analyzed with the analysis being based on a set of network policy data. Based on the analysis, the approach detects network anomalies that correspond to the IoT endpoint devices. These network anomalies and their corresponding IoT endpoint devices are then reported.

Identifying internet of things network anomalies using group attestation

Mechanisms are provided to implement an enhanced privacy deep learning system framework (hereafter 'framework'). The framework receives, from a client computing device, an encrypted first subnet model of a neural network, where the first subnet model is one partition of multiple partitions of the neural network. The framework loads the encrypted first subnet model into a trusted execution environment (TEE) of the framework, decrypts the first subnet model, within the TEE, and executes the first subnet model within the TEE. The framework receives encrypted input data from the client computing device, loads the encrypted input data into the TEE, decrypts the input data, and processes the input data in the TEE using the first subnet model executing within the TEE.

Privacy enhancing deep learning cloud service using a trusted execution environment

An automated method for cyberattack detection and prevention in an endpoint. The technique monitors and protects the endpoint by recording inter-process events, creating an inter-process activity graph based on the recorded inter-process events, matching the inter-process activity (as represented in the activity graph) against known malicious or suspicious behavior (as embodied in a set of one or more pattern graphs), and performing a post-detection operation in response to a match between an inter-process activity and a known malicious or suspicious behavior pattern. Preferably, matching involves matching a subgraph in the activity graph with a known malicious or suspicious behavior pattern as represented in the pattern graph. During this processing, preferably both direct and indirect inter-process activities at the endpoint (or across a set of endpoints) are compared to the known behavior patterns. The approach herein provides for systematic modeling of inter-process behaviors for characterizing malicious or suspicious patterns among processes.

Endpoint inter-process activity extraction and pattern matching

A framework to accurately and quickly verify the ownership of remotely-deployed deep learning models is provided without affecting model accuracy for normal input data. The approach involves generating a watermark, embedding the watermark in a local deep neural network (DNN) model by learning, namely, by training the local DNN model to learn the watermark and a predefined label associated therewith, and later performing a black-box verification against a remote service that is suspected of executing the DNN model without permission. The predefined label is distinct from a true label for a data item in training data for the model that does not include the watermark. Black-box verification includes simply issuing a query that includes a data item with the watermark, and then determining whether the query returns the predefined label.

Protecting deep learning models using watermarking

A computer system extracts features of documents that mention malware programs to determine textual features that correspond to individual ones of the malware programs. The computer system performs analysis of samples of malware programs to determine features corresponding to the samples. The computer system performs clustering using the textual features and using the features that correspond to the samples of the malware programs. The clustering creates clusters of data points, each data point corresponding to an individual one of the malware programs. The clusters contain data points considered by the clustering to be similar. The computer system outputs indications of the clusters to allow determination of whether data points in the clusters correspond to individual ones of specific malwares. Apparatus, methods, and computer program products are disclosed.

Malware clustering approaches based on cognitive computing techniques

A computer-implemented method, a computer program product, and a computer system. The computer system installs and configures a virtual imitating resource in the computer system, wherein the virtual imitating resource imitates a set of resources in the computer system. Installing and configuring the virtual imitating resource includes modifying respective values of an installed version of the virtual imitating resource for an environment of the computer system, determining whether the virtual imitating resource is a static imitating resource or a dynamic imitating resource, and comparing a call graph of the evasive malware with patterns of dynamic imitating resources on a database. The computer system returns a response from an appropriate element of the virtual imitating resource, in response to a call from the evasive malware to a real computing resource, return, by the computer system.

Deactivating evasive malware

Mechanisms are provided to implement a single input, multi-factor authentication (SIMFA) system. The SIMFA system receives a user input for authenticating a user via a single input channel and provides the user input to first authentication logic of an explicit channel of the SIMFA system, where in the first authentication logic performs a knowledge authentication operation on the user input. The SIMFA system further provides the user input to second authentication logic of one or more side channels of the SIMFA system, where the second authentication logic performs authentication on non-knowledge-based characteristics of the user input. The SIMFA system combines results of the first authentication logic and the second authentication logic to generate a final determination of authenticity of the user. The SIMFA system generates an output indicating whether the user is an authentic user or a non-authentic user based on the final determination of authenticity of the user.

Single channel input multi-factor authentication via separate processing pathways

Advanced persistent threats to a mobile device are detected and prevented by leveraging the built-in mandatory access control (MAC) environment in the mobile operating system in a 'stateful' manner. To this end, the MAC mechanism is placed in a permissive mode of operation wherein permission denials are logged but not enforced. The mobile device security environment is augmented to include a monitoring application that is instantiated with system privileges. The application monitors application execution parameters of one or more mobile applications executing on the device. These application execution parameters including, without limitation, the permission denials, are collected and used by the monitoring application to facilitate a stateful monitoring of the operating system security environment. By assembling security-sensitive events over a time period, the system identifies an advanced persistent threat (APT) that otherwise leverages multiple steps using benign components. Once an APT has been detected, a mitigation action (e.g., terminating the malicious process) is undertaken.

Advanced persistent threat (APT) detection in a mobile device

One or more processors mark a set of data fields associated with a first trigger in a first trigger-action pair with a taint, where a trigger event triggers an action event in a trigger-action pair. One or more processors mark a first action associated with the first trigger-action pair with the taint, and detect a second trigger associated with a second trigger-action pair. One or more processors then propagate the taint from the first trigger-action pair to the second trigger, and prevent a second action associated with the second trigger-action pair in response to detecting the taint in the second trigger.

Enforcing access control in trigger-action programming using taint analysis

Approaches to deactivating evasive malware. In an approach, a computer system installs an imitating resource in the computer system and the imitating resource creates an imitating environment of malware analysis, wherein the imitating resource causes the evasive malware to respond to the imitating environment of the malware analysis as to a real environment of the malware analysis. In the imitating environment of malware analysis, the evasive malware determines not to perform malicious behavior. In another approach, a computer system intercepts a call from the evasive malware to a resource on the computer system and returns a virtual resource to the call, wherein in the virtual resource one or more values of the resource on the computer system are modified.

Mechanisms are provided to implement an adversarial network framework. Using an adversarial training technique, an image obfuscation engine operating as a generator in the adversarial network framework is trained to determine a privacy protection layer to be applied by the image obfuscation engine to input image data. The image obfuscation engine applies the determined privacy protection layer to an input image captured by an image capture device to generate obfuscated image data. The obfuscated image data is transmitted to a remotely located image recognition service, via at least one data network, for performance of image recognition operations.

Growing community of inventors

Mahwah, NJ, United States of America

Heqing Huang