Proceedings

Distributed Learning with Adversarial Gradient Perturbations

Nawapon Sangsiri, Yufei Tao

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 4777-4785.

https://doi.org/10.24963/ijcai.2026/532

Keywords

  • Machine Learning: Adversarial machine learning
  • Machine Learning: Federated learning

Abstract

Privacy concerns in distributed learning often lead clients to return intentionally altered gradient information. We consider the problem of learning convex and L-smooth functions under adversarial gradient perturbation, where a client's gradient reply to a server query can deviate arbitrarily from the true gradient subject to a distance bound. Our study focuses on two fundamental questions: (i) what is the smallest achievable sub-optimality gap (i.e., excess error in optimization) under such responses, and (ii) how many queries are sufficient to guarantee a given sub-optimality gap? We establish tight feasibility thresholds on the sub-optimality gap and provide algorithms that achieve these thresholds with provable query complexity guarantees.

Nawapon Sangsiri, and Yufei Tao. 2026. Distributed Learning with Adversarial Gradient Perturbations. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 4777–4785. https://doi.org/10.24963/ijcai.2026/532
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards