Can I read Perceptual Adversarial Robustness: Defense Against Unseen Threat Models on EtoBox?

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models by Laidlaw, Cassidy; Singla, Sahil; Feizi, Soheil is a scholarly article available to read on EtoBox.

What is Perceptual Adversarial Robustness: Defense Against Unseen Threat Models about?

A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the very definition of adversarial attacks that are imperceptible to human eyes. Most current attacks and defenses try to avoid this issue by considering restrictive adversarial threat models such as those bounded by $L_2$ or $L_\infty$ distance, spatial perturbations, etc. However, models that are robust against any of these restrictive threat models are still fragile against other threat models. To resolve this issue, we propose adversarial training against the set of all imperceptible adversarial examples, approximated using deep neural networks. We call this threat model the neural perceptual threat model (NPTM); it includes adversarial examples with a bounded neural perceptual distance (a neural network-based approximation of the true perceptual distance) to natural images. Through an extensive perceptual study, we show that the neural perceptual distance correlates well with human judgements of perceptibility of adversarial examples, validating our threat model. Under the NPTM, we develop novel perceptual adversarial attacks and defenses. Because the N

Author

Laidlaw, Cassidy; Singla, Sahil; Feizi, Soheil

Published

2020

Language

EN