mlsanityData to 14 Oct 2026

FedStrategist: A Meta-Learning Framework for Adaptive and Robust Aggregation in Federated Learning

arXiv 2507.14322 ↗First posted 18 Jul 2025cs.LG cs.CR cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) offers a paradigm for privacy-preserving collaborative AI, but its decentralized nature creates significant vulnerabilities to model poisoning attacks. While numerous static defenses exist, their effectiveness is highly context-dependent, often failing against adaptive adversaries or in heterogeneous data environments. This paper introduces FedStrategist, a novel meta-learning framework that reframes robust aggregation as a real-time, cost-aware control problem. We design a lightweight contextual bandit agent that dynamically selects the optimal aggregation rule from an arsenal of defenses based on real-time diagnostic metrics. Through comprehensive experiments, we demonstrate that no single static rule is universally optimal. We show that our adaptive agent successfully learns superior policies across diverse scenarios, including a ``Krum-favorable" environment and against a sophisticated "stealth" adversary designed to neutralize specific diagnostic signals. Critically, we analyze the paradoxical scenario where a non-robust baseline achieves high but compromised accuracy, and demonstrate that our agent learns a conservative policy to prioritize model integrity. Furthermore, we prove the agent's policy is controllable via a single "risk tolerance" parameter, allowing practitioners to explicitly manage the trade-off between performance and security. Our work provides a new, practical, and analyzable approach to creating resilient and intelligent decentralized AI systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 75 references that are in the map. First posted on arXiv 18 Jul 2025.

Builds on

36 of 75 references.

References · 36

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  3. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  4. 2018Federated Learning with Non-IID Datacited by 1,108
  5. 2019Deep Leakage from Gradientscited by 1,021
  6. 2018How To Backdoor Federated Learningcited by 765
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  9. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  10. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
  11. 2019Free-riders in Federated Learning: Attacks and Defensescited by 49
  12. 2022A Survey on Heterogeneous Federated Learningcited by 42
24 more
  1. 2023An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learningcited by 32
  2. 2025FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectorscited by 19
  3. 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
  4. 2019A Survey of Distributed Consensus Protocols for Blockchain Networkscited by 16
  5. 2022Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregationcited by 8
  6. 2025Reputation as a Solution to Cooperation Collapse in LLM-based MASscited by 8
  7. 2019Security Analysis Methods on Ethereum Smart Contract Vulnerabilities: A Surveycited by 7
  8. 2022Advancing Blockchain-based Federated Learning through Verifiable Off-chain Computationscited by 7
  9. 2022Securing Federated Learning against Overwhelming Collusive Attackerscited by 5
  10. 2023Blockchain-Enabled Federated Learning: A Reference Architecture Design, Implementation, and Verificationcited by 4
  11. 2024Exploring the Practicality of Federated Learning: A Survey Towards the Communication Perspectivecited by 4
  12. 2022MeritRank: Sybil Tolerant Reputation for Merit-based Tokenomicscited by 3
  13. 2024Federated Learning with Dual Attention for Robust Modulation Classification under Attackscited by 3
  14. 2021DID-eFed: Facilitating Federated Learning as a Service with Decentralized Identitiescited by 2
  15. 2024Cryptoeconomics and Tokenomics as Economics: A Survey with Opinionscited by 2
  16. 2025DMPA: Model Poisoning Attacks on Decentralized Federated Learning for Model Differencescited by 2
  17. 2025FedCostAware: Enabling Cost-Aware Federated Learning on the Cloudcited by 2
  18. 2019Engineering Token Economy with System Modelingcited by 1
  19. 2020Efficiency in Digital Economies -- A Primer on Tokenomicscited by 1
  20. 2021A Blockchain-based Trust System for Decentralised Applications: When trustless needs trustcited by 1
  21. 2021Proof-of-Reputation: An Alternative Consensus Mechanism for Blockchain Systemscited by 1
  22. 2023Consensus Algorithms of Distributed Ledger Technology -- A Comprehensive Analysiscited by 1
  23. 2025Secure and Private Federated Learning: Achieving Adversarial Resilience through Robust Aggregationcited by 1
  24. 2025Computational Attestations of Polynomial Integrity Towards Verifiable Machine-Learningcited by 1

Built on by

Not cited yet.