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

NDSS Symposium 2025 Welcome and Opening Remarks

General Chairs: David Balenson, USC Information Sciences Institute and Heng Yin, University of California, Riverside Program Chairs: Christina Pöpper, New York University Abu Dhabi and Hamed Okhravi, MIT Lincoln Laboratory Artifact Evaluation Chairs: Daniele Cono D’Elia, Sapienza University and Mathy Vanhoef, KU Leuven

Read More

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models

Rui Zeng (Zhejiang University), Xi Chen (Zhejiang University), Yuwen Pu (Zhejiang University), Xuhong Zhang (Zhejiang University), Tianyu Du (Zhejiang University), Shouling Ji (Zhejiang University)

Read More

LeoCommon – A Ground Station Observatory Network for LEO...

Eric Jedermann, Martin Böh (University of Kaiserslautern), Martin Strohmeier (armasuisse Science & Technology), Vincent Lenders (Cyber-Defence Campus, armasuisse Science & Technology), Jens Schmitt (University of Kaiserslautern)

Read More

Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces...

Yanzuo Chen (The Hong Kong University of Science and Technology), Zhibo Liu (The Hong Kong University of Science and Technology), Yuanyuan Yuan (The Hong Kong University of Science and Technology), Sihang Hu (Huawei Technologies), Tianxiang Li (Huawei Technologies), Shuai Wang (The Hong Kong University of Science and Technology)

Read More