Using Multiple Self-Supervised Tasks Improves Model Robustness

TL;DR

This paper introduces a defense method for deep networks against adversarial attacks by leveraging multiple self-supervised tasks to enhance model robustness and image intrinsic structure understanding.

Contribution

It is the first to connect multiple self-supervised tasks with robustness, demonstrating improved defense performance over single-task approaches.

Findings

Enhanced robustness against adversarial attacks.

Significant improvement in clean accuracy.

Better intrinsic image structure restoration.

Abstract

Deep networks achieve state-of-the-art performance on computer vision tasks, yet they fail under adversarial attacks that are imperceptible to humans. In this paper, we propose a novel defense that can dynamically adapt the input using the intrinsic structure from multiple self-supervised tasks. By simultaneously using many self-supervised tasks, our defense avoids over-fitting the adapted image to one specific self-supervised task and restores more intrinsic structure in the image compared to a single self-supervised task approach. Our approach further improves robustness and clean accuracy significantly compared to the state-of-the-art single task self-supervised defense. Our work is the first to connect multiple self-supervised tasks to robustness, and suggests that we can achieve better robustness with more intrinsic signal from visual data.