AI RESEARCH
Efficient Encrypted Computation in Convolutional Spiking Neural Networks with TFHE
arXiv CS.LG
•
ArXi:2603.26781v1 Announce Type: cross With the rapid advancement of AI technology, we have seen and concerns on data privacy, leading to some cutting-edge research on machine learning with encrypted computation. Fully Homomorphic Encryption (FHE) is a crucial technology for privacy-preserving computation, while it struggles with continuous non-polynomial functions, as it operates on discrete integers and s only addition and multiplication. Spiking Neural Networks (SNNs), which use discrete spike signals, naturally complement FHE's characteristics. In this paper, we.