Robust Machine Learning Algorithms and Systems for Detection and Mitigation of Adversarial Attacks and Anomalies: Proceedings of a Workshop
Copyright National Academy of Sciences. All rights reserved.
xi
Contents
1 INTRODUCTION 1
2 PLENARY SESSION 3
Sponsor Remarks and Expectations of the Workshop, 3
On Computational Thinking, Inferential Thinking, and Data Science, 3
Machine Learning on Perception: Hype vs. Hope, 4
3 ADVERSARIAL ATTACKS 7
Media Forensics, 7
Forensic Techniques, 10
4 DETECTION AND MITIGATION OF ADVERSARIAL ATTACKS AND ANOMALIES 13
Using AI for Security and Securing AI, 13
Circumventing Defenses to Adversarial Examples, 16
5 ENABLERS OF MACHINE LEARNING ALGORITHMS AND SYSTEMS 19
Impact of Neuroscience on Data Science for Perception, 19
6 RECENT TRENDS IN MACHINE LEARNING, PARTS 1 AND 2 23
On Open Set and Adversarial Issues in Machine Learning, 23
Generative Adversarial Networks (GANs) for Domain Adaptation and Security
Against Attacks, 26
Recent Advances in Optimization for Machine Learning, 29
Forecasting Using Machine Learning, 32
7 PLENARY SESSION 35
Toward Trustworthy Machine Learning, 35
8 RECENT TRENDS IN MACHINE LEARNING, PART 3 39
Domain Adaptation, 39
