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

Secure IP Address Allocation at Cloud Scale

Eric Pauley (University of Wisconsin–Madison), Kyle Domico (University of Wisconsin–Madison), Blaine Hoak (University of Wisconsin–Madison), Ryan Sheatsley (University of Wisconsin–Madison), Quinn Burke (University of Wisconsin–Madison), Yohan Beugin (University of Wisconsin–Madison), Engin Kirda (Northeastern University), Patrick McDaniel (University of Wisconsin–Madison)

Read More

EAGLEYE: Exposing Hidden Web Interfaces in IoT Devices via...

Hangtian Liu (Information Engineering University), Lei Zheng (Institute for Network Sciences and Cyberspace (INSC), Tsinghua University), Shuitao Gan (Laboratory for Advanced Computing and Intelligence Engineering), Chao Zhang (Institute for Network Sciences and Cyberspace (INSC), Tsinghua University), Zicong Gao (Information Engineering University), Hongqi Zhang (Henan Key Laboratory of Information Security), Yishun Zeng (Institute for Network Sciences…

Read More

Poster: Understanding User Acceptance of Privacy Labels: Barriers and...

Jingwen Yan (Clemson University), Mohammed Aldeen (Clemson University), Jalil Harris (Clemson University), Kellen Grossenbacher (Clemson University), Aurore Munyaneza (Texas Tech University), Song Liao (Texas Tech University), Long Cheng (Clemson University)

Read More

WAVEN: WebAssembly Memory Virtualization for Enclaves

Weili Wang (Southern University of Science and Technology), Honghan Ji (ByteDance Inc.), Peixuan He (ByteDance Inc.), Yao Zhang (ByteDance Inc.), Ye Wu (ByteDance Inc.), Yinqian Zhang (Southern University of Science and Technology)

Read More