PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches

• URL: http://arxiv.org/abs/2104.12609v1
• Date: Mon, 26 Apr 2021 14:22:33 GMT
• Title: PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches
• Authors: Chong Xiang, Prateek Mittal
• Abstract summary: An adversarial patch can arbitrarily manipulate image pixels within a restricted region to induce model misclassification. Recent provably robust defenses generally follow the PatchGuard framework by using CNNs with small receptive fields. We extend PatchGuard to PatchGuard++ for provably detecting the adversarial patch attack to boost both provable robust accuracy and clean accuracy.
• Score: 28.94435153159868
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An adversarial patch can arbitrarily manipulate image pixels within a restricted region to induce model misclassification. The threat of this localized attack has gained significant attention because the adversary can mount a physically-realizable attack by attaching patches to the victim object. Recent provably robust defenses generally follow the PatchGuard framework by using CNNs with small receptive fields and secure feature aggregation for robust model predictions. In this paper, we extend PatchGuard to PatchGuard++ for provably detecting the adversarial patch attack to boost both provable robust accuracy and clean accuracy. In PatchGuard++, we first use a CNN with small receptive fields for feature extraction so that the number of features corrupted by the adversarial patch is bounded. Next, we apply masks in the feature space and evaluate predictions on all possible masked feature maps. Finally, we extract a pattern from all masked predictions to catch the adversarial patch attack. We evaluate PatchGuard++ on ImageNette (a 10-class subset of ImageNet), ImageNet, and CIFAR-10 and demonstrate that PatchGuard++ significantly improves the provable robustness and clean performance.

Related papers

• Task-agnostic Defense against Adversarial Patch Attacks [25.15948648034204]
  Adversarial patch attacks mislead neural networks by injecting adversarial pixels within a designated local region. We present PatchZero, a task-agnostic defense against white-box adversarial patches. Our method achieves SOTA robust accuracy without any degradation in the benign performance.
  arXiv  Detail & Related papers  (2022-07-05T03:49:08Z)
• ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking [95.6347501381882]
  Object detectors are found to be vulnerable to physical-world patch hiding attacks. We propose ObjectSeeker as a framework for building certifiably robust object detectors.
  arXiv  Detail & Related papers  (2022-02-03T19:34:25Z)
• Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection [142.24869736769432]
  Adversarial patch attacks pose a serious threat to state-of-the-art object detectors. We propose Segment and Complete defense (SAC), a framework for defending object detectors against patch attacks. We show SAC can significantly reduce the targeted attack success rate of physical patch attacks.
  arXiv  Detail & Related papers  (2021-12-08T19:18:48Z)
• PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier [30.559585856170216]
  adversarial patch attack against image classification models aims to inject adversarially crafted pixels within a localized restricted image region (i.e., a patch) We propose PatchCleanser as a robust defense against adversarial patches that is compatible with any image classification model. We extensively evaluate our defense on the ImageNet, ImageNette, CIFAR-10, CIFAR-100, SVHN, and Flowers-102 datasets.
  arXiv  Detail & Related papers  (2021-08-20T12:09:33Z)
• PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking [46.03749650789915]
  Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. We propose a general defense framework called PatchGuard that can achieve high provable robustness while maintaining high clean accuracy against localized adversarial patches.
  arXiv  Detail & Related papers  (2020-05-17T03:38:34Z)
• Adversarial Training against Location-Optimized Adversarial Patches [84.96938953835249]
  adversarial patches: clearly visible, but adversarially crafted rectangular patches in images. We first devise a practical approach to obtain adversarial patches while actively optimizing their location within the image. We apply adversarial training on these location-optimized adversarial patches and demonstrate significantly improved robustness on CIFAR10 and GTSRB.
  arXiv  Detail & Related papers  (2020-05-05T16:17:00Z)
• PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning [31.255179167694887]
  Patch-based attacks introduce a perceptible but localized change to the input that induces misclassification. Our proposed PatchAttack is query efficient and can break models for both targeted and non-targeted attacks.
  arXiv  Detail & Related papers  (2020-04-12T19:31:09Z)
• Certified Defenses for Adversarial Patches [72.65524549598126]
  Adversarial patch attacks are among the most practical threat models against real-world computer vision systems. This paper studies certified and empirical defenses against patch attacks.
  arXiv  Detail & Related papers  (2020-03-14T19:57:31Z)
• (De)Randomized Smoothing for Certifiable Defense against Patch Attacks [136.79415677706612]
  We introduce a certifiable defense against patch attacks that guarantees for a given image and patch attack size. Our method is related to the broad class of randomized smoothing robustness schemes. Our results effectively establish a new state-of-the-art of certifiable defense against patch attacks on CIFAR-10 and ImageNet.
  arXiv  Detail & Related papers  (2020-02-25T08:39:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.