Paper 2024/1093
Faster Lookup Table Evaluation with Application to Secure LLM Inference
Abstract
As large language models (LLMs) continue to gain popularity, concerns about user privacy are amplified, given that the data submitted by users for inference may contain sensitive information. Therefore, running LLMs through secure two-party computation (a.k.a. secure LLM inference) has emerged as a prominent topic. However, many operations in LLMs, such as Softmax and GELU, cannot be computed using conventional gates in secure computation; instead, lookup tables (LUTs) have to be utilized, which makes LUT to be an essential primitive in secure LLM inference.
In this paper, we propose
Metadata
- Available format(s)
-
PDF
- Category
- Cryptographic protocols
- Publication info
- Preprint.
- Keywords
- Secure Two-Party ComputationLook Up TableSecure Inference
- Contact author(s)
-
xiaoyanghou @ zju edu cn
liujian2411 @ zju edu cn
jingyuli @ zju edu cn
kevinzh @ zju edu cn
kuiren @ zju edu cn - History
- 2024-07-05: approved
- 2024-07-04: received
- See all versions
- Short URL
- https://ia.cr/2024/1093
- License
-
CC BY
BibTeX
@misc{cryptoeprint:2024/1093, author = {Xiaoyang Hou and Jian Liu and Jingyu Li and Jiawen Zhang and Kui Ren}, title = {Faster Lookup Table Evaluation with Application to Secure {LLM} Inference}, howpublished = {Cryptology {ePrint} Archive, Paper 2024/1093}, year = {2024}, url = {https://eprint.iacr.org/2024/1093} }