SplitOut: Out-of-the-Box Training-Hijacking Detection in Split Learning via Outlier Detection
Preprint
Abstract
Split learning enables efficient and privacy-aware training of a deep neural network by splitting a neural network so that the clients (data holders) compute the first layers and only share the intermediate output with the central compute-heavy server. This paradigm introduces a new attack medium in which the server has full control over what the client models learn, which has already been exploited to infer the private data of clients and to implement backdoors in the client models. Although previous work has shown that clients can successfully detect such training-hijacking attacks, the proposed methods rely on heuristics, require tuning of many hyperparameters, and do not fully utilize the clients' capabilities. In this work, we show that given modest assumptions regarding the clients' compute capabilities, an out-of-the-box outlier detection method can be used to detect existing training-hijacking attacks with almost-zero false positive rates. We conclude through experiments on different tasks that the simplicity of our approach we name SplitOut makes it a more viable and reliable alternative compared to the earlier detection methods.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- How to backdoor split learningNeural Networks, 2023
- Split Learning with Differential Privacy for Integrated Terrestrial and Non-Terrestrial NetworksIEEE Wireless Communications, 2023
- Everything is connected: Graph neural networksCurrent Opinion in Structural Biology, 2023
- Algorithms that remember: model inversion attacks and data protection lawPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2018
- Distributed learning of deep neural network over multiple agentsJournal of Network and Computer Applications, 2018
- A comparison of outlier detection algorithms for ITS dataExpert Systems with Applications, 2010
- HIPAA Regulations — A New Era of Medical-Record Privacy?New England Journal of Medicine, 2003
- Approximation capabilities of multilayer feedforward networksNeural Networks, 1991
- Learning representations by back-propagating errorsNature, 1986
- The perceptron: A probabilistic model for information storage and organization in the brain.Psychological Review, 1958