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

Date
2022-11-07
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Print ISSN
Electronic ISSN
Publisher
Association for Computing MachineryNew YorkNYUnited States
Volume
Issue
Pages
125 - 137
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
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.

Course
Other identifiers
Book Title
Keywords
Data privacy, Machine learning, Model inversion, Split learning
Citation
Published Version (Please cite this version)