{"type":"ScholarlyArticle","title":"Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning","authors":[{"name":"Zhiyong Jin","slug":"zhiyong-jin","given":"Zhiyong","family":"Jin","affiliation":""},{"name":"Runhua Xu","slug":"runhua-xu","given":"Runhua","family":"Xu","affiliation":""},{"name":"Chao Li","slug":"chao-li","given":"Chao","family":"Li","affiliation":""},{"name":"Yizhong Liu","slug":"yizhong-liu","given":"Yizhong","family":"Liu","affiliation":""},{"name":"Jianxin Li","slug":"jianxin-li","given":"Jianxin","family":"Li","affiliation":""},{"name":"James Joshi","slug":"james-joshi","given":"James","family":"Joshi","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/73","url":"https://ijcai.org/proceedings/2026/73","pdf":"https://ijcai.org/proceedings/2026/0073.pdf","markdown":"https://ijcai.org/proceedings/2026/73.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/73","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI Ethics, Trust, Fairnes","track":"Main Track","number":73,"pages":{"first":644,"last":651},"keywords":["AI Ethics, Trust, Fairnes: Safety and robustness","AI Ethics, Trust, Fairnes: Trustworthy AI"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}