mlsanityData to 7 Oct 2026

LOGSAFE: Logic-Guided Verification for Trustworthy Federated Time-Series Learning

arXiv 2411.03231 ↗First posted 5 Nov 2024cs.CR cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces LOGSAFE, a defense mechanism for federated learning in time series settings, particularly within cyber-physical systems. It addresses poisoning attacks by moving beyond traditional update-similarity methods and instead using logical reasoning to evaluate client reliability. LOGSAFE extracts client-specific temporal properties, infers global patterns, and verifies clients against them to detect and exclude malicious participants. Experiments show that it significantly outperforms existing methods, achieving up to 93.27% error reduction over the next best baseline. Our code is available at https://github.com/judydnguyen/LOGSAFE-Robust-FTS.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 38 of its 70 references that are in the map. First posted on arXiv 5 Nov 2024.

Builds on

38 of 70 references.

References · 38

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  6. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 869
  7. 2018How To Backdoor Federated Learningcited by 745
  8. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 555
  10. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  11. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  12. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
26 more
  1. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  2. 2018Analyzing Federated Learning through an Adversarial Lenscited by 346
  3. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 330
  4. 2019Robust Aggregation for Federated Learningcited by 314
  5. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  6. 2019Can You Really Backdoor Federated Learning?cited by 250
  7. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
  8. 2021Federated Learning for Smart Healthcare: A Surveycited by 182
  9. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  10. 2020Byzantine-Robust Learning on Heterogeneous Datasets via Bucketingcited by 125
  11. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 119
  12. 2019Efficient Parameter-free Clustering Using First Neighbor Relationscited by 96
  13. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  14. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  15. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  16. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 78
  17. 2023Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneitycited by 64
  18. 2021Cluster-driven Graph Federated Learning over Multiple Domainscited by 43
  19. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directionscited by 33
  20. 2023Multi-metrics adaptively identifies backdoors in Federated learningcited by 23
  21. 2021Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Seriescited by 21
  22. 2022Federated Learning for 5G Base Station Traffic Forecastingcited by 15
  23. 2020Data Poisoning Attacks on Regression Learning and Corresponding Defensescited by 10
  24. 2022Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applicationscited by 4
  25. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspectioncited by 4
  26. 2024Formal Logic Enabled Personalized Federated Learning Through Property Inferencecited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023TrustFed: A Reliable Federated Learning Framework with Malicious-Attack Resistance
  2. 2024Federated Time Series Generation on Feature and Temporally Misaligned Data
  3. 2024Fake or Compromised? Making Sense of Malicious Clients in Federated Learning
  4. 2026FERA: Uncertainty-Aware Federated Reasoning for Large Language Models
  5. 2026QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting
  6. 2026FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation
  7. 2023LR-XFL: Logical Reasoning-based Explainable Federated Learning
  8. 2024Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting