Adversarial Attacks and Defences Competition

The chapter describes the structure and outcomes of the NIPS 2017 competition focused on generating and defending against adversarial examples in machine learning classifiers.

Open

Year: 2018
Venue: arXiv 2018
ArXiv: arxiv.org/abs/1804.00097
URL: arxiv.org/abs/1804.00097
Authors: 23
Hosting: Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text: arxiv.org/abs/1804.00097ARXIV-DEFAULT
TL;DR: Semantic Scholar

Attribution policy →

Abstract

To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop new ways to defend against them. In this chapter, we describe the structure and organization of the competition and the solutions developed by several of the top-placing teams.