SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification

Ashwinee Panda, Saeed Mahloujifar, Arjun N. Bhagoji, Supriyo Chakraborty, Prateek Mittal

Research output: Contribution to journalConference articlepeer-review

31 Scopus citations

Abstract

Federated learning is inherently vulnerable to model poisoning attacks because its decentralized nature allows attackers to participate with compromised devices. In model poisoning attacks, the attacker reduces the model's performance on targeted sub-tasks (e.g. classifying planes as birds) by uploading "poisoned" updates. In this report we introduce SparseFed, a novel defense that uses global top-k update sparsification and device-level gradient clipping to mitigate model poisoning attacks. We propose a theoretical framework for analyzing the robustness of defenses against poisoning attacks, and provide robustness and convergence analysis of our algorithm. To validate its empirical efficacy we conduct an open-source evaluation at scale across multiple benchmark datasets for computer vision and federated learning.

Original languageEnglish (US)
Pages (from-to)7587-7624
Number of pages38
JournalProceedings of Machine Learning Research
Volume151
StatePublished - 2022
Event25th International Conference on Artificial Intelligence and Statistics, AISTATS 2022 - Virtual, Online, Spain
Duration: Mar 28 2022Mar 30 2022

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Fingerprint

Dive into the research topics of 'SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsification'. Together they form a unique fingerprint.

Cite this