ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking

Chong Xiang, Alexander Valtchanov, Saeed Mahloujifar, Prateek Mittal

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

3 Scopus citations

Abstract

Object detectors, which are widely deployed in security-critical systems such as autonomous vehicles, have been found vulnerable to patch hiding attacks. An attacker can use a single physically-realizable adversarial patch to make the object detector miss the detection of victim objects and undermine the functionality of object detection applications. In this paper, we propose ObjectSeeker for certifiably robust object detection against patch hiding attacks. The key insight in ObjectSeeker is patch-agnostic masking: we aim to mask out the entire adversarial patch without knowing the shape, size, and location of the patch. This masking operation neutralizes the adversarial effect and allows any vanilla object detector to safely detect objects on the masked images. Remarkably, we can evaluate ObjectSeeker's robustness in a certifiable manner: we develop a certification procedure to formally determine if ObjectSeeker can detect certain objects against any white-box adaptive attack within the threat model, achieving certifiable robustness. Our experiments demonstrate a significant (~10%-40% absolute and ~2-6× relative) improvement in certifiable robustness over the prior work, as well as high clean performance (∼1% drop compared with undefended models).

Original languageEnglish (US)
Title of host publicationProceedings - 44th IEEE Symposium on Security and Privacy, SP 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1329-1347
Number of pages19
ISBN (Electronic)9781665493369
DOIs
StatePublished - 2023
Event44th IEEE Symposium on Security and Privacy, SP 2023 - Hybrid, San Francisco, United States
Duration: May 22 2023May 25 2023

Publication series

NameProceedings - IEEE Symposium on Security and Privacy
Volume2023-May
ISSN (Print)1081-6011

Conference

Conference44th IEEE Symposium on Security and Privacy, SP 2023
Country/TerritoryUnited States
CityHybrid, San Francisco
Period5/22/235/25/23

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Software
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking'. Together they form a unique fingerprint.

Cite this