paper
referenced-only
2018
paper:arxiv-1809-02104

Are adversarial examples inevitable?

ByAli Shafahi·W. R. Huang·Christoph Studer·S. Feizi·T. Goldstein
Original abstract (expand)

A wide range of defenses have been proposed to harden neural networks against adversarial attacks. However, a pattern has emerged in which the majority of adversarial defenses are quickly broken by new attacks. Given the lack of success at generating robust defenses, we are led to ask a fundamental question: Are adversarial attacks inevitable? This paper analyzes adversarial examples from a theoretical perspective, and identifies fundamental bounds on the susceptibility of a classifier to adversarial attacks. We show that, for certain classes of problems, adversarial examples are inescapable. Using experiments, we explore the implications of theoretical guarantees for real-world problems and discuss how factors such as dimensionality and image complexity limit a classifier's robustness against adversarial examples.

Similar preprints — Semantic Scholar

Cited by (1)