CipherFormer: Efficient Transformer Private Inference with Low Round Complexity

arXiv:2403.16860v1 Announce Type: new
Abstract: There is a growing trend to outsource the inference task of large transformer models to cloud servers. However, this poses a severe threat to users' private data as they are exposed to cloud servers after uploading. Although several works attempted to provide private inference for transformer models, their hundreds of communication rounds limit the application scenarios. Motivated by the desire to minimize round complexity, we propose CipherFormer, a novel transformer private inference scheme using homomorphic …

arxiv cloud complexity cs.cr data exposed large low private private data servers task threat trend