Adversarial Representation Sharing: A Quantitative and Secure Collaborative Learning Framework

no code implementations • 27 Mar 2022 • Jikun Chen, Feng Qiang, Na Ruan

Then we present ARS, a collaborative learning framework wherein users share representations of data to train models, and add imperceptible adversarial noise to data representations against reconstruction or attribute extraction attacks.

Attribute Attribute Extraction +3