Nanyang Technological University

Ben-gurion University of the Negev Research and Development Authority

Datakrew Pte. Ltd.

Anupam Chattopadhyay

Yuval Elovici

Rami Puzis

Polina Zilberman

Siew Kei Lam

Arpan Jati

Elad Marco

Aviad Elitzur

Sumanta Bose

Thambipillai Srikanthan

Naina Gupta

Jawad Haj-Yahya

Nandish Chattopadhyay

A framework for efficiently and automatically exploring a data network and accurately identifying network threats, which comprises a plurality of software and hardware-based agents, distributed over the data network. The agents are capable of adjusting or reconfiguring, on the fly, the behavior of the agents and their ability to collect data in a targeted manner, so as to investigate suspicious incidents and alerts and collect data that was not yet collected by the system; collecting forensic data by executing tasks defined in workflows, being distributed threat intercepting programs and reporting about the collected forensic data, back to a Central Control Unit (C&C). Distributed threat intercepting programs ('workflows') are used to provide instructions to agents, to perform branching and provide instructions to the Central Control Unit (C&C), which orchestrates the agents to assure proper execution of the workflows; analyzes the collected information and presents ongoing status to an operator supervising the data network.

Bio-inspired agile cyber-security assurance framework

Disclosed herein is a system for watermarking a neural network, comprising memory; and at least one processor in communication with the memory; wherein the memory stores instructions for causing the at least one processor to carry out a method comprising: generating a trigger set by obtaining examples from a training set by random sampling from the training set, respective examples being associated with respective true classes of a plurality of classes; generating a set of adversarial examples by structured perturbation of the examples; generating, for each adversarial example, one or more adversarial class labels by passing the adversarial example to the neural network; and applying one or more trigger labels to each said adversarial example, wherein the one or more trigger labels are selected randomly from the plurality of classes, and wherein each trigger label is not a said true class label for the corresponding example or a said adversarial class label for the corresponding adversarial example; and storing the adversarial examples and corresponding trigger labels as the trigger set; and performing a tuning process to adjust parameters at each layer of the neural network using the trigger set, to thereby generate a watermarked neural network.

Methods and systems for watermarking neural networks

Gateway and bridge devices for internet of things systems are described. The gateway device is configured to communicate with a server using signals encrypted according to a first encryption protocol and to communicate with bridge device using signals encrypted with a second protocol. The bridge device is configured to decrypt the signals received from the gateway device and to communicate with sensors and actuators. The bridge device is further configured to encrypt data signals from the sensors for sending to the gateway device.

Gateway and bridge devices for secure internet of things

Growing community of inventors

Singapore, Singapore

Anupam Chattopadhyay