Work

Fall of Empires: Breaking Byzantine-tolerant SGD by Inner Product Manipulation

Year: 2019
Type: preprint
Abstract: Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robust aggregation methods for synchronous SGD -- coordinate-wise median and Krum -- can be broken using new attack strategies based on inner product manipulation. We prove our results theoretically, as well as show empirical validation.
Language: English
Open Access status: green
OpenAlex ID: W2922259313
Cites: 29
Cited by: 183
Related to: 10