SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learning. (arXiv:2108.09052v3 [cs.CR] UPDATED)

Distributed deep learning frameworks such as split learning provide great
benefits with regards to the computational cost of training deep neural
networks and the privacy-aware utilization of the collective data of a group of
data-holders. Split learning, in particular, achieves this goal by dividing a
neural network between a client and a server so that the client computes the
initial set of layers, and the server computes the rest. However, this method
introduces a unique attack vector for a malicious …

attacks hijacking split learning training