Chapter 6: Evaluating gradient inversion attacks and defenses

Yangsibo Huanga; Samyak Guptab; Zhao Songc; Sanjeev Arorab; Kai Lib    aElectrical and Computer Engineering, Princeton University, Princeton, NJ, United StatesbPrinceton University, Princeton, NJ, United StatescAdobe Research, San Jose, CA, United States

Abstract

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of federated learning, whereby malicious eavesdroppers or participants in the protocol can partially recover the clients' private data. This chapter summarizes existing attacks in federated learning, and investigates their potential limitations. The chapter then presents an evaluation of the benefits of several ...

Get Federated Learning now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.