Phillip Rieger (Technical University of Darmstadt), Alessandro Pegoraro (Technical University of Darmstadt), Kavita Kumari (Technical University of Darmstadt), Tigist Abera (Technical University of Darmstadt), Jonathan Knauer (Technical University of Darmstadt), Ahmad-Reza Sadeghi (Technical University of Darmstadt)

Split Learning (SL) is a distributed deep learning approach enabling multiple clients and a server to collaboratively train and infer on a shared deep neural network (DNN) without requiring clients to share their private local data. The DNN is partitioned in SL, with most layers residing on the server and a few initial layers and inputs on the client side. This configuration allows resource-constrained clients to participate in training and inference. However, the distributed architecture exposes SL to backdoor attacks, where malicious clients can manipulate local datasets to alter the DNN's behavior. Existing defenses from other distributed frameworks like Federated Learning are not applicable, and there is a lack of effective backdoor defenses specifically designed for SL.

We present SafeSplit, the first defense against client-side backdoor attacks in Split Learning (SL). SafeSplit enables the server to detect and filter out malicious client behavior by employing circular backward analysis after a client's training is completed, iteratively reverting to a trained checkpoint where the model under examination is found to be benign. It uses a two-fold analysis to identify client-induced changes and detect poisoned models. First, a static analysis in the frequency domain measures the differences in the layer's parameters at the server. Second, a dynamic analysis introduces a novel rotational distance metric that assesses the orientation shifts of the server's layer parameters during training. Our comprehensive evaluation across various data distributions, client counts, and attack scenarios demonstrates the high efficacy of this dual analysis in mitigating backdoor attacks while preserving model utility.

View More Papers

”Who is Trying to Access My Account?” Exploring User...

Tongxin Wei (Nankai University), Ding Wang (Nankai University), Yutong Li (Nankai University), Yuehuan Wang (Nankai University)

Read More

On the Robustness of LDP Protocols for Numerical Attributes...

Xiaoguang Li (Xidian University, Purdue University), Zitao Li (Alibaba Group (U.S.) Inc.), Ninghui Li (Purdue University), Wenhai Sun (Purdue University, West Lafayette, USA)

Read More

Enhancing Security in Third-Party Library Reuse – Comprehensive Detection...

Shangzhi Xu (The University of New South Wales), Jialiang Dong (The University of New South Wales), Weiting Cai (Delft University of Technology), Juanru Li (Feiyu Tech), Arash Shaghaghi (The University of New South Wales), Nan Sun (The University of New South Wales), Siqi Ma (The University of New South Wales)

Read More

Rediscovering Method Confusion in Proposed Security Fixes for Bluetooth

Maximilian von Tschirschnitz (Technical University of Munich), Ludwig Peuckert (Technical University of Munich), Moritz Buhl (Technical University of Munich), Jens Grossklags (Technical University of Munich)

Read More