English

Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing

Machine Learning 2024-03-05 v1

Abstract

Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks. Although several heuristic defenses are proposed to enhance the robustness of federated learning, they do not provide certifiable robustness guarantees. In this paper, we incorporate randomized smoothing techniques into federated adversarial training to enable data-private distributed learning with certifiable robustness to test-time adversarial perturbations. Our experiments show that such an advanced federated adversarial learning framework can deliver models as robust as those trained by the centralized training. Further, this enables provably-robust classifiers to 2\ell_2-bounded adversarial perturbations in a distributed setup. We also show that one-point gradient estimation based training approach is 23×2-3\times faster than popular stochastic estimator based approach without any noticeable certified robustness differences.

Keywords

Cite

@article{arxiv.2103.16031,
  title  = {Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing},
  author = {Cheng Chen and Bhavya Kailkhura and Ryan Goldhahn and Yi Zhou},
  journal= {arXiv preprint arXiv:2103.16031},
  year   = {2024}
}

Comments

9 pages, 12 figures

R2 v1 2026-06-24T00:40:28.913Z