Understanding Byzantine Robustness in Federated Learning with A Black-box Server

August 12, 2024 ยท Entered Twilight ยท ๐Ÿ› arXiv.org

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: .flake8, .github, .gitignore, .pre-commit-config.yaml, .style.yapf, LICENSE, README.md, benchmark, doc, environment, federatedscope, materials, meta.yaml, scripts, setup.py, tests

Authors Fangyuan Zhao, Yuexiang Xie, Xuebin Ren, Bolin Ding, Shusen Yang, Yaliang Li arXiv ID 2408.06042 Category cs.CR: Cryptography & Security Cross-listed cs.AI Citations 1 Venue arXiv.org Repository https://github.com/alibaba/FederatedScope/tree/Byzantine_attack_defense โญ 1510 Last Checked 3 months ago
Abstract
Federated learning (FL) becomes vulnerable to Byzantine attacks where some of participators tend to damage the utility or discourage the convergence of the learned model via sending their malicious model updates. Previous works propose to apply robust rules to aggregate updates from participators against different types of Byzantine attacks, while at the same time, attackers can further design advanced Byzantine attack algorithms targeting specific aggregation rule when it is known. In practice, FL systems can involve a black-box server that makes the adopted aggregation rule inaccessible to participants, which can naturally defend or weaken some Byzantine attacks. In this paper, we provide an in-depth understanding on the Byzantine robustness of the FL system with a black-box server. Our investigation demonstrates the improved Byzantine robustness of a black-box server employing a dynamic defense strategy. We provide both empirical evidence and theoretical analysis to reveal that the black-box server can mitigate the worst-case attack impact from a maximum level to an expectation level, which is attributed to the inherent inaccessibility and randomness offered by a black-box server.The source code is available at https://github.com/alibaba/FederatedScope/tree/Byzantine_attack_defense to promote further research in the community.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Cryptography & Security