mlsanityData to 14 Oct 2026

STAR-FL: Secure Federated Learning with Spatial-Temporal Analysis and Robust Aggregation

arXiv 2608.14861 ↗First posted 14 Aug 2026cs.CR cs.LGcited by 0

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two key challenges remain for existing defense techniques: (1) accurately distinguishing between benign and malicious model updates and (2) effectively mitigating the influence of poisoned model updates during model aggregation. To address these challenges, we propose a novel defense framework against targeted poisoning attacks with Spatial-Temporal Analysis and Robust aggregation for FL (STAR-FL). First, we employ spatial-temporal clustering to identify and remove potentially malicious updates from the FL training process. Second, we adjust the learning rate during aggregation to mitigate the impact of any malicious updates that evade detection. Third, we conduct extensive experiments across multiple benchmark datasets to evaluate the spatial-temporal analysis and robust aggregation in STAR-FL. Experimental results demonstrate their synergistic effect in enabling STAR-FL to effectively protect FL and consistently outperform state-of-the-art defenses against targeted poisoning attacks, significantly reducing Attack Success Rates (ASRs). The source code is available at https://github.com/mlsysx/STAR-FL.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 23 of its 31 references that are in the map. First posted on arXiv 14 Aug 2026.

Builds on

23 of 31 references.

References · 23

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  6. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  7. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  8. 2019Robust Aggregation for Federated Learningcited by 317
  9. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  10. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  11. 2018Mitigating Sybils in Federated Learning Poisoningcited by 161
  12. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
11 more
  1. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 98
  2. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  3. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
  4. 2019Byzantine-Robust Federated Machine Learning through Adaptive Model Averagingcited by 70
  5. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 68
  6. 2020Mitigating Backdoor Attacks in Federated Learningcited by 39
  7. 2023Label Poisoning is All You Needcited by 29
  8. 2023On the Vulnerability of Backdoor Defenses for Federated Learningcited by 27
  9. 2023Privacy Risks Analysis and Mitigation in Federated Learning for Medical Imagescited by 7
  10. 2024On the Efficiency of Privacy Attacks in Federated Learningcited by 3
  11. 2024Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  2. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
  3. 2024Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning
  4. 2023G2uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering
  5. 2024Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
  6. 2022FL-Defender: Combating Targeted Attacks in Federated Learning
  7. 2022FedCC: Robust Federated Learning against Model Poisoning Attacks
  8. 2024Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense