Accurate Split Learning on Noisy Signals

Hang Xu, Aritra Dutta, Xin Li, Panos Kalnis

Keywords: Split Learning, Denoising techniques

Abstract: Noise injection is applied in Split Learning to address privacy concerns about data leakage. Previous works protect Split Learning by adding noise to the intermediate results during the forward pass. Unfortunately, noisy signals significantly degrade the accuracy of Split Learning training. This paper focuses on improving the training accuracy of Split Learning over noisy signals while protecting training data from reconstruction attacks. We propose two denoising techniques, namely scaling and random masking. Our theoretical results show that both of our denoising techniques accurately estimate the intermediate variables during the forward pass of Split Learning. Moreover, our experiments with deep neural networks demonstrate that the proposed denoising approaches allow Split Learning to tolerate high noise levels while achieving almost the same accuracy as the noise-free baseline. Interestingly, we show that after applying our denoising techniques, the resultant network is more resilient against a state-of-the-art attack compared to the simple noise injection approach.

Primary Area: optimization

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10717