mlsanityData to 14 Oct 2026

A First Order Meta Stackelberg Method for Robust Federated Learning

arXiv 2306.13800 ↗First posted 23 Jun 2023cs.LG cs.GTcited by 7

Not on the map. Why?

Abstract (arXiv)

Previous research has shown that federated learning (FL) systems are exposed to an array of security risks. Despite the proposal of several defensive strategies, they tend to be non-adaptive and specific to certain types of attacks, rendering them ineffective against unpredictable or adaptive threats. This work models adversarial federated learning as a Bayesian Stackelberg Markov game (BSMG) to capture the defender's incomplete information of various attack types. We propose meta-Stackelberg learning (meta-SL), a provably efficient meta-learning algorithm, to solve the equilibrium strategy in BSMG, leading to an adaptable FL defense. We demonstrate that meta-SL converges to the first-order varepsilon-equilibrium point in O(varepsilon-2) gradient iterations, with O(varepsilon-4) samples needed per iteration, matching the state of the art. Empirical evidence indicates that our meta-Stackelberg framework performs exceptionally well against potent model poisoning and backdoor attacks of an uncertain nature.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 36 of its 58 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

36 of 58 references.

References · 36

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  4. 2018How To Backdoor Federated Learningcited by 765
  5. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  6. 2016Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Conditioncited by 539
  7. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 503
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  9. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  10. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  11. 2020FLTrust: Byzantine-robust Federated Learning via Trust Bootstrappingcited by 346
  12. 2019Robust Aggregation for Federated Learningcited by 317
24 more
  1. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  2. 2019A Little Is Enough: Circumventing Defenses For Distributed Learningcited by 288
  3. 2019Can You Really Backdoor Federated Learning?cited by 255
  4. 2020Bilevel Optimization: Convergence Analysis and Enhanced Designcited by 222
  5. 2019Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methodscited by 148
  6. 2019Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulationcited by 141
  7. 2017Lower Bounds for Finding Stationary Points Icited by 126
  8. 2023A Fully First-Order Method for Stochastic Bilevel Optimizationcited by 100
  9. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
  10. 2019ES-MAML: Simple Hessian-Free Meta Learningcited by 57
  11. 2022MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statisticcited by 55
  12. 2020Mitigating Backdoor Attacks in Federated Learningcited by 39
  13. 2020Dif-MAML: Decentralized Multi-Agent Meta-Learningcited by 26
  14. 2021The Confluence of Networks, Games and Learningcited by 26
  15. 2019What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?cited by 20
  16. 2021FLAME: Taming Backdoors in Federated Learning (Extended Version 1)cited by 16
  17. 2023Scenario-Agnostic Zero-Trust Defense with Explainable Threshold Policy: A Meta-Learning Approachcited by 12
  18. 2021Dynamic population-based meta-learning for multi-agent communication with natural languagecited by 10
  19. 2022Meta-Learning in Gamescited by 10
  20. 2023On the Price of Transparency: A Comparison between Overt Persuasion and Covert Signalingcited by 9
  21. 2023Learning to Backdoor Federated Learningcited by 8
  22. 2015Hardness Results for Signaling in Bayesian Zero-Sum and Network Routing Gamescited by 5
  23. 2022Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysiscited by 5
  24. 2022Stackelberg Meta-Learning for Strategic Guidance in Multi-Robot Trajectory Planningcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 1.

7 papers.

  1. 2024Symbiotic Game and Foundation Models for Cyber Deception Operations in Strategic Cyber Warfarecited by 8
  2. 2024Multi-level Traffic-Responsive Tilt Camera Surveillance through Predictive Correlated Online Learningcited by 6
  3. 2023Self-Confirming Transformer for Belief-Conditioned Adaptation in Offline Multi-Agent Reinforcement Learningcited by 4
  4. 2025From Texts to Shields: Convergence of Large Language Models and Cybersecuritycited by 4
  5. 2025Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigationcited by 4
  6. 2025Agentic AI for Cyber Resilience: A New Security Paradigm and Its System-Theoretic Foundationscited by 4
  7. 2026Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimizationcited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2023A First Order Meta Stackelberg Method for Robust Federated Learning (Technical Report) ↗
  2. 2024Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
  3. 2021Meta Federated Learning
  4. 2026Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learning
  5. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
  6. 2021Robust Federated Learning with Attack-Adaptive Aggregation
  7. 2022Invariant Aggregator for Defending against Federated Backdoor Attacks
  8. 2024FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning