Using Multiple Self-Supervised Tasks Improves Model Robustness
This addresses the robustness issue in computer vision for security-critical applications, representing an incremental advance by extending single-task self-supervised defenses.
The paper tackles the problem of deep networks failing under adversarial attacks by proposing a defense that dynamically adapts inputs using multiple self-supervised tasks, resulting in significant improvements in robustness and clean accuracy compared to state-of-the-art single-task defenses.
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.