Privacy Preserving Discretized Spiking Neural Network with TFHE

Artificial intelligence not only offers significant convenience but also raises privacy and security concerns, which pose challenges for Spiking Neural Networks (SNNs). Fully Homomorphic Encryption (FHE) is a crucial privacy-preserving computation technology, and the discrete nature of SNNs naturally aligns with FHE’s requirements. In this paper, we construct a framework to evaluate the homomorphic computation of SNN named FHE-DiSNN that enables SNN to achieve good prediction performance on encrypted data. First, benefitting from the discrete nature of spike signals, our proposed model avoids the errors introduced by discretizing activation functions. Second, by applying bootstrapping, we design new privacy-preserving functions FHE-Fire and FHE-Reset, through which noise can be refreshed, allowing us to evaluate SNN for an arbitrary number of operations. Furthermore, we improve the computational efficiency of FHE-DiSNN while maintaining a high level of accuracy. Finally, we evaluate our model on the MNIST dataset. The experiments show that FHE-DiSNN with 30 neurons in the hidden layer achieves a minimum prediction accuracy of 94.4%. Under optimal parameters, it achieves a 95.1% accuracy, with only a 0.6% decrease compared to the original SNN (95.7%). These results demonstrate the superiority of SNN over second-generation neural networks for homomorphic evaluation.