THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption. (arXiv:2206.00216v1 [cs.CR])

As more and more pre-trained language models adopt on-cloud deployment, the
privacy issues grow quickly, mainly for the exposure of plain-text user data
(e.g., search history, medical record, bank account). Privacy-preserving
inference of transformer models is on the demand of cloud service users. To
protect privacy, it is an attractive choice to compute only with ciphertext in
homomorphic encryption (HE). However, enabling pre-trained models inference on
ciphertext data is difficult due to the complex computations in transformer
blocks, which are …

arxiv encryption homomorphic encryption inference privacy transformer