Certified Robustness to Clean-label Poisoning Using Diffusion Denoising

Sanghyun Hong, Nicholas Carlini, Alexey KurakinSubmission to ICLR 2025 · Withdrawn

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

We present a certified defense to clean-label poisoning attacks. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain $\ell_2$-norm bounded adversarial perturbations into the training data to induce a targeted misclassification of a test-time input. Inspired by the adversarial robustness achieved by \emph{denoised smoothing}, we show how an off-the-shelf diffusion model can sanitize the tampered training data. We extensively test our defense against seven clean-label poisoning attacks and reduce their attack success to 0-16% with only a negligible drop in the test time accuracy. We compare our defense with existing countermeasures against clean-label poisoning, showing that the defense reduces the attack success the most and offers the best model utility. Our results highlight the need for future work on developing stronger clean-label attacks and using our certified yet practical defense as a strong baseline to evaluate these attacks.
BibTeX
@misc{hong2024certified,
  author = {Sanghyun Hong and Nicholas Carlini and Alexey Kurakin},
  title = {{Certified Robustness to Clean-label Poisoning Using Diffusion Denoising}},
  year = {2024},
  eprint = {2403.11981},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.11981},
}
Figure