Adversary-resilient Distributed and Decentralized Statistical Inference and Machine Learning: An Overview of Recent Advances Under the Byzantine Threat Model
This work tackles the problem of securing distributed and decentralized frameworks against adversarial threats for practitioners and researchers in cybersecurity and machine learning, but it is incremental as it reviews existing advances.
The paper provides an overview of recent algorithmic approaches that ensure robustness in distributed and decentralized inference and machine learning against Byzantine adversarial attacks, addressing cybersecurity threats in data-driven systems.
While the last few decades have witnessed a huge body of work devoted to inference and learning in distributed and decentralized setups, much of this work assumes a non-adversarial setting in which individual nodes---apart from occasional statistical failures---operate as intended within the algorithmic framework. In recent years, however, cybersecurity threats from malicious non-state actors and rogue entities have forced practitioners and researchers to rethink the robustness of distributed and decentralized algorithms against adversarial attacks. As a result, we now have a plethora of algorithmic approaches that guarantee robustness of distributed and/or decentralized inference and learning under different adversarial threat models. Driven in part by the world's growing appetite for data-driven decision making, however, securing of distributed/decentralized frameworks for inference and learning against adversarial threats remains a rapidly evolving research area. In this article, we provide an overview of some of the most recent developments in this area under the threat model of Byzantine attacks.