Cryptographic inference for large language model via secret sharing
Inference services based on large language models may lead to the leakage of user input hints to the server or proprietary model weights to the user. Cryptographic techniques such as secure multi-party computation and homomorphic encryption provide feasible solutions to the above problems, but they...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2025-06-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025115/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849424504328028160 |
|---|---|
| author | CHENG Ke XIA Yuheng DAI Chuanyun FU Jiaxuan ZHU Xinghui SHEN Yulong |
| author_facet | CHENG Ke XIA Yuheng DAI Chuanyun FU Jiaxuan ZHU Xinghui SHEN Yulong |
| author_sort | CHENG Ke |
| collection | DOAJ |
| description | Inference services based on large language models may lead to the leakage of user input hints to the server or proprietary model weights to the user. Cryptographic techniques such as secure multi-party computation and homomorphic encryption provide feasible solutions to the above problems, but they are still difficult to apply practically to the task of inference over large language models due to the excessive computational and communication overhead. Based on this, a lightweight secret-sharing-based cryptographic inference scheme for large language models was proposed, by which inference could be performed efficiently and accurately while ensuring that neither user inputs nor model parameters were revealed. The experimental results show that the proposed scheme improves the efficiency by 1.2~10 times and reduces the communication cost by 20%~90% compared with the existing state-of-the-art works. |
| format | Article |
| id | doaj-art-e325f767d11e4e3d9a84644ad2bdec92 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2025-06-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-e325f767d11e4e3d9a84644ad2bdec922025-08-20T03:30:09ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2025-06-0146168184114258215Cryptographic inference for large language model via secret sharingCHENG KeXIA YuhengDAI ChuanyunFU JiaxuanZHU XinghuiSHEN YulongInference services based on large language models may lead to the leakage of user input hints to the server or proprietary model weights to the user. Cryptographic techniques such as secure multi-party computation and homomorphic encryption provide feasible solutions to the above problems, but they are still difficult to apply practically to the task of inference over large language models due to the excessive computational and communication overhead. Based on this, a lightweight secret-sharing-based cryptographic inference scheme for large language models was proposed, by which inference could be performed efficiently and accurately while ensuring that neither user inputs nor model parameters were revealed. The experimental results show that the proposed scheme improves the efficiency by 1.2~10 times and reduces the communication cost by 20%~90% compared with the existing state-of-the-art works.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025115/privacy-preservinglarge language modelsecret sharingsecure multi-party computationcryptographic inference |
| spellingShingle | CHENG Ke XIA Yuheng DAI Chuanyun FU Jiaxuan ZHU Xinghui SHEN Yulong Cryptographic inference for large language model via secret sharing Tongxin xuebao privacy-preserving large language model secret sharing secure multi-party computation cryptographic inference |
| title | Cryptographic inference for large language model via secret sharing |
| title_full | Cryptographic inference for large language model via secret sharing |
| title_fullStr | Cryptographic inference for large language model via secret sharing |
| title_full_unstemmed | Cryptographic inference for large language model via secret sharing |
| title_short | Cryptographic inference for large language model via secret sharing |
| title_sort | cryptographic inference for large language model via secret sharing |
| topic | privacy-preserving large language model secret sharing secure multi-party computation cryptographic inference |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025115/ |
| work_keys_str_mv | AT chengke cryptographicinferenceforlargelanguagemodelviasecretsharing AT xiayuheng cryptographicinferenceforlargelanguagemodelviasecretsharing AT daichuanyun cryptographicinferenceforlargelanguagemodelviasecretsharing AT fujiaxuan cryptographicinferenceforlargelanguagemodelviasecretsharing AT zhuxinghui cryptographicinferenceforlargelanguagemodelviasecretsharing AT shenyulong cryptographicinferenceforlargelanguagemodelviasecretsharing |