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...
Bewaard in:
| Hoofdauteurs: | , , , , , |
|---|---|
| Formaat: | Artigo |
| Taal: | Chinês |
| Gepubliceerd in: |
Editorial Department of Journal on Communications
2025-06-01
|
| Reeks: | Tongxin xuebao |
| Onderwerpen: | |
| Online toegang: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2025115/ |
| Tags: |
Geen labels, Wees de eerste die dit record labelt!
|