2019 International Conference On Computer Aided Design

The Premier Conference Devoted to Technical Innovations in Electronic Design Automation

November 4-7, 2019The Westin Westminster Westminster, CO

v class="event-details"> MP Associates, Inc.

TUESDAY November 06, 1:45pm - 3:45pm | Capri

Is Adversarial Learning a Threat for Machine Learning? Defense Strategies and Design of Better Machine Learners!
Houman Homayoun - George Mason Univ.
Sam Gu - FutureWei Technologies, Inc.
In the recent years, Machine Learning (ML) especially mammalian brain inspired neural networks (including deep neural networks (DNNs)) have demonstrated an impressive performance and robustness to noise in different domains ranging from medical imaging, autonomous driving to defense applications. Despite DNNs being robust to noise and perturbations, recent research works have exploited the vulnerabilities and showed that the DNNs can be fooled by adding specially crafted perturbations to the input. In this session, first talk will introduce the challenges of ML in adversarial settings. This will be followed by two talks on making the ML inference robust to adversarial attacks in robotics and security domains. The last talk will provide an analysis of different adversarial attacks and solution to improve the efficiency of existing defense techniques.

6D.1Robust Object Estimation using Generative-Discriminative Inference for Secure Robotics Applications
 Speaker: R. Iris Bahar - Brown Univ.
 Authors: Zhefan Ye - Univ. of Michigan
Odest Chadwicke Jenkins - Univ. of Michigan
Shiyang Lu - Univ. of Michigan
Zhiqiang Sui - Univ. of Michigan
R. Iris Bahar - Brown Univ.
Alessandro Costantini - Brown Univ.
Yanqi Liu - Brown Univ.
6D.2Adversarial Evasion Resilient Hardware Malware Detectors
 Speaker: Nael Abu-Ghazaleh - Univ. of California, Riverside
 Authors: Khaled Khasawneh - Univ. of California, Riverside
Dmitry Ponomarev - Binghamton Univ.
Lei Yu - Binghamton Univ.
Nael Abu-Ghazaleh - Univ. of California, Riverside
6D.3 Efficient Utilization of Adversarial Training towards Robust Machine Learners and its Analysis
 Speaker: Sai Manoj - George Mason Univ.
 Authors: Sai Manoj - George Mason Univ.
Sairaj Amberkar - George Mason Univ.
Setareh Rafatirad - George Mason Univ.
Houman Homayoun - George Mason Univ.