---
title: "Distributed Learning with Adversarial Gradient Perturbations"
authors:
  - "Nawapon Sangsiri"
  - "Yufei Tao"
doi: "10.24963/ijcai.2026/532"
url: "https://ijcai.org/proceedings/2026/532"
pdf: "https://ijcai.org/proceedings/2026/0532.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "4777-4785"
track: "Main Track"
keywords:
  - "Machine Learning: Adversarial machine learning"
  - "Machine Learning: Federated learning"
---

# Distributed Learning with Adversarial Gradient Perturbations

Nawapon Sangsiri, Yufei Tao

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 4777-4785. DOI: [10.24963/ijcai.2026/532](https://doi.org/10.24963/ijcai.2026/532)

## 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.