mlsanityData to 14 Oct 2026

Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks

arXiv 2410.17431 ↗First posted 22 Oct 2024cs.LG cs.CR cs.GTcited by 9

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to specific types of attacks, leaving them insufficient in the face of multiple uncertain, unknown, and adaptive attacks employing diverse strategies. This work formulates adversarial federated learning under a mixture of various attacks as a Bayesian Stackelberg Markov game, based on which we propose the meta-Stackelberg defense composed of pre-training and online adaptation. The gist is to simulate strong attack behavior using reinforcement learning (RL-based attacks) in pre-training and then design meta-RL-based defense to combat diverse and adaptive attacks. We develop an efficient meta-learning approach to solve the game, leading to a robust and adaptive FL defense. Theoretically, our meta-learning algorithm, meta-Stackelberg learning, provably converges to the first-order varepsilon-meta-equilibrium point in O(varepsilon-2) gradient iterations with O(varepsilon-4) samples per iteration. Experiments show that our meta-Stackelberg framework performs superbly against strong model poisoning and backdoor attacks of uncertain and unknown types.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 51 of its 83 references that are in the map. First posted on arXiv 22 Oct 2024.

Builds on

51 of 83 references.

References · 51

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  8. 2019Advances and Open Problems in Federated Learningcited by 3,046
  9. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  10. 2014Conditional Generative Adversarial Netscited by 2,162
  11. 2021Variational Diffusion Modelscited by 1,153
  12. 2018On First-Order Meta-Learning Algorithmscited by 1,018
38 more
  1. 2019Towards Federated Learning at Scale: System Designcited by 832
  2. 2018How To Backdoor Federated Learningcited by 765
  3. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  4. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  5. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 565
  6. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  7. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 539
  8. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  9. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  11. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  12. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  13. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  14. 2019Robust Aggregation for Federated Learningcited by 317
  15. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  16. 2019Can You Really Backdoor Federated Learning?cited by 255
  17. 2020Bilevel Optimization: Convergence Analysis and Enhanced Designcited by 222
  18. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  19. 2019Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methodscited by 148
  20. 2020A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Criticcited by 144
  21. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  22. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  23. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 84
  24. 2020Defending against Backdoors in Federated Learning with Robust Learning Ratecited by 82
  25. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
  26. 2022MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statisticcited by 55
  27. 2019Zeno++: Robust Fully Asynchronous SGDcited by 53
  28. 2020Mitigating Backdoor Attacks in Federated Learningcited by 39
  29. 2019Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Datacited by 38
  30. 2021The Confluence of Networks, Games and Learningcited by 26
  31. 2020On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learningcited by 19
  32. 2020Multi-agent Reinforcement Learning in Bayesian Stackelberg Markov Games for Adaptive Moving Target Defensecited by 15
  33. 2017BLENDER: Enabling Local Search with a Hybrid Differential Privacy Modelcited by 14
  34. 2024Conjectural Online Learning with First-order Beliefs in Asymmetric Information Stochastic Gamescited by 14
  35. 2023Scenario-Agnostic Zero-Trust Defense with Explainable Threshold Policy: A Meta-Learning Approachcited by 12
  36. 2023On the Price of Transparency: A Comparison between Overt Persuasion and Covert Signalingcited by 9
  37. 2023Learning to Backdoor Federated Learningcited by 8
  38. 2022Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysiscited by 5

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 2.

9 papers.

  1. 2025In-Context Reinforcement Learning via Communicative World Modelscited by 5
  2. 2025From Texts to Shields: Convergence of Large Language Models and Cybersecuritycited by 4
  3. 2025Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigationcited by 4
  4. 2025Agentic AI for Cyber Resilience: A New Security Paradigm and Its System-Theoretic Foundationscited by 4
  5. 2025Stackelberg Coupling of Online Representation Learning and Reinforcement Learningcited by 1
  6. 2024The Game-Theoretic Symbiosis of Trust and AI in Networked Systemscited by 0
  7. 2025Traffic Adaptive Moving-window Service Patrolling for Real-time Incident Management during High-impact Eventscited by 0
  8. 2026Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisitioncited by 0
  9. 2026Secure-CHG: A Comprehensive Framework for Robust and Fair Federated Learning via Hybrid Defense and Contribution-Aware Trustcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023A First Order Meta Stackelberg Method for Robust Federated Learning
  2. 2023A First Order Meta Stackelberg Method for Robust Federated Learning (Technical Report) ↗
  3. 2021Meta Federated Learning
  4. 2026Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learning
  5. 2025Provably Robust Federated Reinforcement Learning
  6. 2021Robust Federated Learning with Attack-Adaptive Aggregation
  7. 2025POLAR: Policy-based Layerwise Reinforcement Learning Method for Stealthy Backdoor Attacks in Federated Learning
  8. 2024FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning