Encrypted-SNN: A Privacy-Preserving Method for Converting Artificial Neural Networks to Spiking Neural Networks

The transformation from Artificial Neural Networks (ANNs) to Spiking Neural Networks (SNNs) presents a formidable challenge, particularly in terms of preserving privacy to safeguard sensitive data during the conversion process. In response to these privacy concerns, a novel Encrypted-SNN approach is proposed for the ANN-SNN conversion. By incorporating noise into the gradients of both ANNs and SNNs, privacy protection without compromising network performance can be enhanced. The proposed method is tested using popular datasets including CIFAR10, MNIST, and Fashion MNIST, achieving respective accuracies of 88.1 \(\%\) , 99.3 \(\%\) , and 93.0 \(\%\) respectively. The influence of three distinct privacy budgets ( \(\epsilon \)  = 0.5, 1.0, and 1.6) on the accuracy of the model are also discussed. Experimental results demonstrate that the Encrypted-SNN approach effectively optimizes the balance between privacy and performance. This has practical implications for data privacy protection and contributes to the enhancement of security and privacy within SNNs.