PatchGuard: A provably robust defense against adversarial patches via small receptive fields and masking

Chong Xiang, Arjun Nitin Bhagoji, Vikash Sehwag, Prateek Mittal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial patch to the object to be misclassified, and defending against such attacks is an unsolved/open problem. In this paper, we propose a general defense framework called PatchGuard that can achieve high provable robustness while maintaining high clean accuracy against localized adversarial patches. The cornerstone of PatchGuard involves the use of CNNs with small receptive fields to impose a bound on the number of features corrupted by an adversarial patch. Given a bounded number of corrupted features, the problem of designing an adversarial patch defense reduces to that of designing a secure feature aggregation mechanism. Towards this end, we present our robust masking defense that robustly detects and masks corrupted features to recover the correct prediction. Notably, we can prove the robustness of our defense against any adversary within our threat model. Our extensive evaluation on ImageNet, ImageNette (a 10-class subset of ImageNet), and CIFAR-10 datasets demonstrates that our defense achieves state-of-the-art performance in terms of both provable robust accuracy and clean accuracy.

Original languageEnglish (US)
Title of host publicationProceedings of the 30th USENIX Security Symposium
PublisherUSENIX Association
Pages2237-2254
Number of pages18
ISBN (Electronic)9781939133243
StatePublished - 2021
Event30th USENIX Security Symposium, USENIX Security 2021 - Virtual, Online
Duration: Aug 11 2021Aug 13 2021

Publication series

NameProceedings of the 30th USENIX Security Symposium

Conference

Conference30th USENIX Security Symposium, USENIX Security 2021
CityVirtual, Online
Period8/11/218/13/21

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'PatchGuard: A provably robust defense against adversarial patches via small receptive fields and masking'. Together they form a unique fingerprint.

Cite this