English

Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification

Cryptography and Security 2024-10-30 v3

Abstract

Face authentication systems have brought significant convenience and advanced developments, yet they have become unreliable due to their sensitivity to inconspicuous perturbations, such as adversarial attacks. Existing defenses often exhibit weaknesses when facing various attack algorithms and adaptive attacks or compromise accuracy for enhanced security. To address these challenges, we have developed a novel and highly efficient non-deep-learning-based image filter called the Iterative Window Mean Filter (IWMF) and proposed a new framework for adversarial purification, named IWMF-Diff, which integrates IWMF and denoising diffusion models. These methods can function as pre-processing modules to eliminate adversarial perturbations without necessitating further modifications or retraining of the target system. We demonstrate that our proposed methodologies fulfill four critical requirements: preserved accuracy, improved security, generalizability to various threats in different settings, and better resistance to adaptive attacks. This performance surpasses that of the state-of-the-art adversarial purification method, DiffPure.

Keywords

Cite

@article{arxiv.2408.10673,
  title  = {Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification},
  author = {Hanrui Wang and Ruoxi Sun and Cunjian Chen and Minhui Xue and Lay-Ki Soon and Shuo Wang and Zhe Jin},
  journal= {arXiv preprint arXiv:2408.10673},
  year   = {2024}
}

Comments

Accepted in IEEE Transactions on Dependable and Secure Computing

R2 v1 2026-06-28T18:17:53.096Z