mlsanityData to 14 Oct 2026

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

arXiv 2505.01454 ↗First posted 30 Apr 2025cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 30 Apr 2025.

Builds on

18 of 36 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018How To Backdoor Federated Learningcited by 765
  6. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  8. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  9. 2019Robust Aggregation for Federated Learningcited by 317
  10. 2017Sparse Communication for Distributed Gradient Descentcited by 249
  11. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  12. 2020Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approachcited by 81
6 more
  1. 2019Understanding Top-k Sparsification in Distributed Deep Learningcited by 56
  2. 2018Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communicationcited by 51
  3. 2021DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learningcited by 41
  4. 2024Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregationcited by 15
  5. 2023FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Schedulercited by 13
  6. 2023FLTracer: Accurate Poisoning Attack Provenance in Federated Learningcited by 8

Built on by

Not cited yet.