Adversarial Attacks and Defences Competition
This addresses the problem of improving machine learning security against adversarial attacks for researchers and practitioners, but it is incremental as it builds on existing competition frameworks.
Google Brain organized a NIPS 2017 competition to accelerate research on adversarial examples and robustness in machine learning classifiers, focusing on developing new methods for generating and defending against such attacks, with top teams' solutions described.
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.