Attacks on Robust Distributed Learning Schemes via Sensitivity Curve Maximization

Abstract

Distributed learning paradigms, such as federated or decentralized learning, allow a collection of agents to solve global learning and optimization problems through limited local interactions. Most such strategies rely on a mixture of local adaptation and aggregation steps, either among peers or at a central fusion center. Classically, aggregation in distributed learning is based on averaging, which is statistically efficient, but susceptible to attacks by even a small number of malicious agents. This observation has motivated a number of recent works, which develop robust aggregation schemes by employing robust variations of the mean. We present a new attack based on sensitivity curve maximization (SCM), and demonstrate that it is able to disrupt existing robust aggregation schemes by injecting small, but effective perturbations.

References in corpus (8)

• Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
• The Hidden Vulnerability of Distributed Learning in Byzantium
• Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent
• Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
• Threats to Federated Learning: A Survey
• ByRDiE: Byzantine-resilient distributed coordinate descent for decentralized learning
• BRIDGE: Byzantine-resilient Decentralized Gradient Descent
• MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks