Byzantine-Resilient Secure Federated Learning on Low-Bandwidth Networks

An On-Demand Byzantine-Resilient Secure Routing Protocol for Wireless Adhoc Networks

Security has become a primary concern in order to provide protected communication between mobile nodes in a hostile environment. We refer to any arbitrary action by authenticated nodes resulting in disruption of the routing service such as drop packets, modify packets and miss-route packets as Byzantine behavior, and to such an adversary as a Byzantine adversary. Nodes may exhibit Byzantine beh...

Secure SNMP-Based Network Management in Low Bandwidth Networks

ByRDiE: Byzantine-resilient distributed coordinate descent for decentralized learning

Distributed machine learning algorithms enable processing of datasets that are distributed over a network without gathering the data at a centralized location. While efficient distributed algorithms have been developed under the assumption of faultless networks, failures that can render these algorithms nonfunctional indeed happen in the real world. This paper focuses on the problem of Byzantin...

Optimal Byzantine Resilient Convergence in Asynchronous Robots Networks

We propose the first deterministic algorithm that tolerates up to f byzantine faults in 3f + 1-sized networks and performs in the asynchronous CORDA model. Our solution matches the previously established lower bound for the semi-synchronous ATOM model on the number of tolerated Byzantine robots. Our algorithm works under bounded scheduling assumptions for oblivious robots moving in a uni-dimens...

Practical Secure Aggregation for Federated Learning on User-Held Data

Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on mobile devices, wherein Secure Aggregatio...