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

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

doi:10.24963/ijcai.2026/73

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

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 644-651.

https://doi.org/10.24963/ijcai.2026/73

Keywords

AI Ethics, Trust, Fairnes: Safety and robustness
AI Ethics, Trust, Fairnes: Trustworthy AI

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.

Zhiyong Jin, Runhua Xu, Chao Li, Yizhong Liu, Jianxin Li, and James Joshi. 2026. Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 644–651. https://doi.org/10.24963/ijcai.2026/73

@inproceedings{ijcai2026p73,
  title     = {Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning},
  author    = {Jin, Zhiyong and Xu, Runhua and Li, Chao and Liu, Yizhong and Li, Jianxin and Joshi, James},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {644--651},
  year      = {2026},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2026/73},
  url       = {https://doi.org/10.24963/ijcai.2026/73},
}

TY  - CPAPER
TI  - Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning
AU  - Jin, Zhiyong
AU  - Xu, Runhua
AU  - Li, Chao
AU  - Liu, Yizhong
AU  - Li, Jianxin
AU  - Joshi, James
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 644
EP  - 651
DO  - 10.24963/ijcai.2026/73
UR  - https://doi.org/10.24963/ijcai.2026/73
ER  -