Join the workshop by entering JVCC.

Find Event Hall 8 and type in the passcode of the workshop.

https://cdc2020.ieeecss.org/jvcc.php

If you do not have the passcode, please send your request to qz494@nyu.edu.

Introduction

This workshop aims at the confluence between security and learning, which become more apparent and essential for multi-agent systems. Learning theory provides a set of useful analytic and decision-making tools for a wide range of applications in multi-agent systems, including vision-based robotics, and data-driven control systems. On the other hand, a growing number of adversarial attacks and malicious behaviors aimed at systems built with machine learning and optimization algorithms calls for new security theories and models for better undestanding and safeguarding such systems.

This workshop will gather experts from the cybersecurity, machine learning, and control communities to highlight recent works that contribute to addressing challenges arising from the intersection beween learning and security. This workshop will provide tutorials on adversarial learning problems and learning methods for security to students and early-career researchers and for a wider audience, it will give an overview of the current research activities in applications, especially in networked control systems, cybersecurity, Internet of Things, and cyber-physical systems. Furthermore, new research directions related to security and learning in multi-agent systems will be discussed for advancing knowledge and technology and expanding the community.

Workshop Organizers

• Quanyan Zhu, quanyan.zhu@nyu.edu

Department of Electrical and Computer Engineering,

Tandon School of Engineering, New York University

• Hideaki Ishii, ishii@c.titech.ac.jp

Department of Computer Science, School of Computing,

Tokyo Institute of Technology