SplitGuard: Detecting and mitigating training-hijacking attacks in split learning

Date

2022-11-07

Editor(s)

Advisor

Supervisor

Co-Advisor

Co-Supervisor

Instructor

BUIR Usage Stats
1
views
44
downloads

Citation Stats

Attention Stats

Series

Abstract

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 server attempting to steal the client's private data: the server can direct the client model towards learning any task of its choice, e.g. towards outputting easily invertible values. With a concrete example already proposed (Pasquini et al., CCS '21), such training-hijacking attacks present a significant risk for the data privacy of split learning clients. In this paper, we propose SplitGuard, a method by which a split learning client can detect whether it is being targeted by a training-hijacking attack or not. We experimentally evaluate our method's effectiveness, compare it with potential alternatives, and discuss in detail various points related to its use. We conclude that SplitGuard can effectively detect training-hijacking attacks while minimizing the amount of information recovered by the adversaries. © 2022 Owner/Author.

Source Title

Publisher

Association for Computing MachineryNew YorkNYUnited States

Course

Other identifiers

Book Title

Degree Discipline

Degree Level

Degree Name

Citation

Published Version (Please cite this version)

Language

English