Secure Transformer Inference Protocol

arXiv:2312.00025v2 Announce Type: replace
Abstract: Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT. While recent strides in secure two-party protocols have successfully addressed security concerns in serving Transformer models, their adoption is practically infeasible due to the prohibitive cryptographic overheads involved. Drawing insights from our hands-on experience in developing two real-world Transformer-based services, we identify the inherent efficiency bottleneck in the two-party assumption. To overcome this limitation, we propose a novel three-party threat …

adoption arxiv chatgpt critical cryptographic cs.cr cs.lg data drawing experience hands-on experience insights party protocol protocols security security concerns services user data