Synergistic Neuromorphic Federated Learning with ANN-SNN Conversion For Privacy Protection

Yingni Chen, Shikuang Deng, Yuhang Li, Xin Dong, Shi Gu

Abstract: Federated Learning (FL) has been widely explored for the growing public data privacy issues, where only model parameters are communicated instead of private data. However, recent studies debunk the privacy protection of FL, showing that private data can be leaked from the communicated gradients or parameters updates. In this paper, we propose a framework called Synergistic Neuromorphic Federated Learning (SNFL) that enhances privacy during FL. Before uploading the updates of the client model, SNFL first converts clients' Artificial Neural Networks (ANNs) to Spiking Neural Networks (SNNs) via calibration algorithms. In a way that not only loses almost no accuracy but also encrypts the client model's parameters, SNFL manages to obtain a more performant model with high privacy. After aggregation of various SNNs parameters, server distributes the parameters back to clients to continue training under ANN architecture, providing smooth convergence. The proposed framework is demonstrated to be private, introducing a lightweight overhead as well as yielding prominent performance boosts. Extensive experiments with different kinds of datasets have demonstrated the efficacy and practicability of our method. In most of our experimental IID and not extreme Non-IID scenarios, the SNFL technique has significantly enhanced the model performance. For instance, SNFL improve the accuracy of FedAvg on Tiny-ImageNet by 13.79%. In the IID situation of tiny-ImageNet, for instance, the SNFL method is 13.79% more accurate than FedAvg. Also, the original image cannot be reconstructed after 280 iterations of attacks with the SNFL method, whereas it can be reconstructed after just 70 iterations with FedAvg.

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.

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: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)