Exploiting Certified Defences to Attack Randomised Smoothing

Andrew Craig Cullen, Paul Montague, Shijie Liu, Sarah Monazam Erfani, Benjamin I. P. Rubinstein

Abstract

Certified guarantees of adversarial robustness play an important role in providing assurances regarding a models output, irrespective of the behaviour of an attacker. However, while the development of such guarantees has drawn upon an improved understanding of attacker behaviour, so too can certified guarantees be exploited in order to generate more efficient adversarial attacks. Within this work, we explore this heretofore undiscovered additional attack surface, while also considering how previously discovered attacks could be applied to models defended by randomised smoothing. In all bar one experiment our approach generates smaller adversarial perturbations for more than $70 \%$ of tested samples, reducing the average magnitude of the adversarial perturbation by $13 \%$.
BibTeX
@inproceedings{cullen2023exploiting,
  author = {Andrew Craig Cullen and Paul Montague and Shijie Liu and Sarah Monazam Erfani and Benjamin I. P. Rubinstein},
  title = {{Exploiting Certified Defences to Attack Randomised Smoothing}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=AeTl9sbF-VT},
}

Loading related content...

Figure