Homomorphic WiSARDs: Efficient Weightless Neural Network training over encrypted data

arXiv:2403.20190v1 Announce Type: cross
Abstract: The widespread application of machine learning algorithms is a matter of increasing concern for the data privacy research community, and many have sought to develop privacy-preserving techniques for it. Among existing approaches, the homomorphic evaluation of ML algorithms stands out by performing operations directly over encrypted data, enabling strong guarantees of confidentiality. The homomorphic evaluation of inference algorithms is practical even for relatively deep Convolution Neural Networks (CNNs). However, training is still a major challenge, …

abstract algorithms application arxiv community cs.cr cs.lg data data privacy encrypted data evaluation machine machine learning machine learning algorithms matter ml algorithms network network training neural network operations privacy research research community training type