A First Order Meta Stackelberg Method for Robust Federated Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningMeta-LearningModel PoisoningSimilar Papers 제목 키워드 기반
Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks
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 insuf…
Federated LearningMeta-LearningModel PoisoningReinforcement Learning (RL)Meta-Computing Enhanced Federated Learning in IIoT: Satisfaction-Aware Incentive Scheme via DRL-Based Stackelberg Game
The Industrial Internet of Things (IIoT) leverages Federated Learning (FL) for distributed model training while preserving data privacy, and meta-computing enhances FL by optimizing and integrating distributed computing …
Deep Reinforcement LearningDistributed ComputingFederated LearningOn the Computational Complexity of Stackelberg Planning and Meta-Operator Verification: Technical Report
Stackelberg planning is a recently introduced single-turn two-player adversarial planning model, where two players are acting in a joint classical planning task, the objective of the first player being hampering the seco…
MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning
We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or…
Meta-LearningStackelberg Meta-Learning Based Control for Guided Cooperative LQG Systems
Guided cooperation allows intelligent agents with heterogeneous capabilities to work together by following a leader-follower type of interaction. However, the associated control problem becomes challenging when the leade…
Meta-Learning