Bant: Byzantine Antidote via Trial Function and Trust Scores

Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structures remain vulnerable to malicious influences. In this paper, we address a specific threat: Byzantine attacks, wherein compromised clients inject adversarial updates to derail global convergence. We combine the concept of trust scores with trial function methodology to dynamically filter outliers. Our methods address the critical limitations of previous approaches, allowing operation even when Byzantine nodes are in the majority. Moreover, our algorithms adapt to widely used scaled methods such as Adam and RMSProp, as well as practical scenarios, including local training and partial participation. We validate the robustness of our methods by conducting extensive experiments on both public datasets and private ECG data collected from medical institutions. Furthermore, we provide a broad theoretical analysis of our algorithms and their extensions to the aforementioned practical setups. The convergence guaranties of our methods are comparable to those of classical algorithms developed without Byzantine interference.

Authors

• Gleb Molodtsov Moscow Independent Research Institute of Artificial Intelligence Basic Research of Artificial Intelligence Laboratory (BRAIn Lab) Federated Learning Problems Laboratory Innopolis University
• Daniil Medyakov Moscow Independent Research Institute of Artificial Intelligence Basic Research of Artificial Intelligence Laboratory (BRAIn Lab) Federated Learning Problems Laboratory
• Sergey Skorik Trusted AI Research Center, RAS
• Nikolas Khachaturov Russian-Armenian University
• Shahane Tigranyan Institute for Informatics and Automation Problems, NAS RA
• Vladimir Aletov Moscow Independent Research Institute of Artificial Intelligence Basic Research of Artificial Intelligence Laboratory (BRAIn Lab) Federated Learning Problems Laboratory
• Aram Avetisyan Trusted AI Research Center, RAS
• Martin Takáč Mohamed bin Zayed University of Artificial Intelligence
• Aleksandr Beznosikov Ivannikov Institute for System Programming of the Russian Academy of Sciences Moscow Institute of Physics and Technology Sber AI Lab Skoltech

Keywords

No keywords are indexed for this paper.