TSS: Transformation-Specific Smoothing for Robustness Certification

Linyi Li, Maurice Weber, Xiaojun Xu, Luka Rimanic, Bhavya Kailkhura, Tao Xie, Ce Zhang, Bo Li

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

Abstract

As machine learning (ML) systems become pervasive, safeguarding their security is critical. However, recently it has been demonstrated that motivated adversaries are able to mislead ML systems by perturbing test data using semantic transformations. While there exists a rich body of research providing provable robustness guarantees for ML models against Lp bounded adversarial perturbations, guarantees against semantic perturbations remain largely underexplored. In this paper, we provide TSS-a unified framework for certifying ML robustness against general adversarial semantic transformations. First, depending on the properties of each transformation, we divide common transformations into two categories, namely resolvable (e.g., Gaussian blur) and differentially resolvable (e.g., rotation) transformations. For the former, we propose transformation-specific randomized smoothing strategies and obtain strong robustness certification. The latter category covers transformations that involve interpolation errors, and we propose a novel approach based on stratified sampling to certify the robustness. Our framework TSS leverages these certification strategies and combines with consistency-enhanced training to provide rigorous certification of robustness. We conduct extensive experiments on over ten types of challenging semantic transformations and show that TSS significantly outperforms the state of the art. Moreover, to the best of our knowledge, TSS is the first approach that achieves nontrivial certified robustness on the large-scale ImageNet dataset. For instance, our framework achieves 30.4% certified robust accuracy against rotation attack (within ±30°) on ImageNet. Moreover, to consider a broader range of transformations, we show TSS is also robust against adaptive attacks and unforeseen image corruptions such as CIFAR-10-C and ImageNet-C.

Original languageEnglish (US)
Title of host publicationCCS 2021 - Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security
PublisherAssociation for Computing Machinery
Pages535-557
Number of pages23
ISBN (Electronic)9781450384544
DOIs
StatePublished - Nov 12 2021
Event27th ACM Annual Conference on Computer and Communication Security, CCS 2021 - Virtual, Online, Korea, Republic of
Duration: Nov 15 2021Nov 19 2021

Publication series

NameProceedings of the ACM Conference on Computer and Communications Security
ISSN (Print)1543-7221

Conference

Conference27th ACM Annual Conference on Computer and Communication Security, CCS 2021
Country/TerritoryKorea, Republic of
CityVirtual, Online
Period11/15/2111/19/21

Keywords

  • certified robustness
  • semantic transformation attacks

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'TSS: Transformation-Specific Smoothing for Robustness Certification'. Together they form a unique fingerprint.

Cite this