---
title: "Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning"
authors:
  - "Zhiyong Jin"
  - "Runhua Xu"
  - "Chao Li"
  - "Yizhong Liu"
  - "Jianxin Li"
  - "James Joshi"
doi: "10.24963/ijcai.2026/73"
url: "https://ijcai.org/proceedings/2026/73"
pdf: "https://ijcai.org/proceedings/2026/0073.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "644-651"
track: "Main Track"
keywords:
  - "AI Ethics, Trust, Fairnes: Safety and robustness"
  - "AI Ethics, Trust, Fairnes: Trustworthy AI"
---

# Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning

Zhiyong Jin, Runhua Xu, Chao Li, Yizhong Liu, Jianxin Li, James Joshi

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 644-651. DOI: [10.24963/ijcai.2026/73](https://doi.org/10.24963/ijcai.2026/73)

## Abstract

Gradient sparsification, while mitigating communication bottlenecks in Federated Learning (FL), fundamentally alters the geometric landscape of model updates. We reveal that the resultant high-dimensional orthogonality renders traditional Euclidean-based robust aggregation metrics mathematically ambiguous, creating a sparsity-robustness trade-off that adversaries exploit to bypass detection. To resolve this structural dissonance, we propose SafeSparse, a consensus restoration framework that decouples defense into topological and semantic dimensions. Unlike prior arts that treat sparsification and security orthogonally, SafeSparse introduces: (1) a Structure-Aware Calibration mechanism utilizing Jaccard similarity to filter topological outliers induced by index poisoning; and (2) a Directional Semantic Alignment module employing density-based clustering on update signs to neutralize magnitude-invariant attacks. Theoretically, we establish convergence guarantees for SafeSparse. Extensive experiments across multiple datasets and attack scenarios demonstrate that SafeSparse  recovers up to 25.7% global accuracy under coordinated poisoning, effectively closing the vulnerability gap in communication-efficient FL.