Efficient Certified Defenses Against Patch Attacks on Image Classifiers
Adversarial patches pose a realistic threat model for physical world attacks on autonomous systems via their perception component. Autonomous systems in safety-critical domains such as automated driving should thus contain a fail-safe fallback component that combines certifiable robustness against patches with efficient inference while maintaining high performance on clean inputs. We propose BagCert, a novel combination of model architecture and certification procedure that allows efficient certification. We derive a loss that enables end-to-end optimization of certified robustness against patches of different sizes and locations. On CIFAR10, BagCert certifies 10.000 examples in 43 seconds on a single GPU and obtains 86% clean and 60% certified accuracy against 5x5 patches.
Code (0)
등록된 구현이 없습니다.
Tasks
GPUSimilar Papers 제목 키워드 기반
Certified Defenses for Adversarial Patches
Adversarial patch attacks are among one of the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against patch attacks. We begin with a set of ex…
ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses tow…
(De)Randomized Smoothing for Certifiable Defense against Patch Attacks
Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In th…
Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches
The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e.g., autonomous driving, content moderation, biometr…
Autonomous DrivingCertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models
Vision-Language-Action (VLA) policies are vulnerable to localized physical perturbations, yet existing certified patch defenses target discrete labels and cannot directly certify continuous, temporally correlated actions…