Search Results for author:
Found 4 papers, 3 papers with code
Defense Mechanisms Against Training-Hijacking Attacks in Split Learning
Split learning achieves this by splitting a neural network between a client and a server such that the client computes the initial set of layers, and the server computes the rest.
Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning
The Centered Clipping framework (ICML 2021) has further shown that, besides reducing the variance, the momentum term from the previous iteration can be used as a reference point to neutralize the Byzantine attacks and show impressive performance against well-known attacks.
UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learning
(1) We show that an honest-but-curious split learning server, equipped only with the knowledge of the client neural network architecture, can recover the input samples and obtain a functionally similar model to the client model, without being detected.
SplitGuard: Detecting and Mitigating Training-Hijacking Attacks in Split Learning
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.
