Defense Against the Dark Arts: An overview of adversarial example security research and future research directions

TL;DR

This paper reviews current defenses against adversarial examples in deep learning, summarizes the state of the art, and suggests future research directions to improve security.

Contribution

It provides a comprehensive overview of adversarial example defenses and outlines future research challenges and directions in this field.

Findings

Summary of current defense techniques

Identification of key challenges in adversarial robustness

Recommendations for future research directions

Abstract

This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and provides recommendations for future research directions on this topic.