2025/04/17 by John Y.L. Chiang, Chiang, John
Computer Science · #Chaos-based Image/Signal Encryption #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Privacy-Preserving Technologies in Data
paper · pdf · doi:10.48550/arxiv.2504.12623
openalex publication_date 2025/04/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we present the demonstration of training a four-layer neural network entirely using fully homomorphic encryption (FHE), supporting both single-output and multi-output classification tasks in a non-interactive setting. A key contribution of our work is identifying that replacing Softmax with Sigmoid, in conjunction with the Binary Cross-Entropy (BCE) loss function, provides an effective and scalable solution for homomorphic classification. Moreover, we show that the BCE loss function, originally designed for multi-output tasks, naturally extends to the multi-class setting, thereby enabling broader applicability. We also highlight the limitations of prior loss functions such as the SLE loss and the one proposed in the 2019 CVPR Workshop, both of which suffer from vanishing gradients as network depth increases. To address the challenges posed by large-scale encrypted data, we further introduce an improved version of the previously proposed data encoding scheme, Double Volley Revolver, which achieves a better trade-off between computational and memory efficiency, making FHE-based neural network training more practical. The complete, runnable C++ code to implement our work can be found at: \hrefhttps://github.com/petitioner/ML.NNtraininghttps://github.com/petitioner/ML.NNtraining.