Secure Byzantine-Robust Machine Learning
This addresses the problem of secure and robust collaborative training for edge devices and servers, representing an incremental advancement by integrating multiple existing concerns.
The paper tackles the challenge of combining robustness, privacy, and security in distributed machine learning by proposing a secure two-server protocol that provides input privacy and Byzantine-robustness, achieving communication-efficiency, fault-tolerance, and local differential privacy.
Increasingly machine learning systems are being deployed to edge servers and devices (e.g. mobile phones) and trained in a collaborative manner. Such distributed/federated/decentralized training raises a number of concerns about the robustness, privacy, and security of the procedure. While extensive work has been done in tackling with robustness, privacy, or security individually, their combination has rarely been studied. In this paper, we propose a secure two-server protocol that offers both input privacy and Byzantine-robustness. In addition, this protocol is communication-efficient, fault-tolerant and enjoys local differential privacy.