Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2501.08336 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929676435324928 |
|---|---|
| author | Zhao, Jiahao Nan, Jiayi Wei, Lai Yang, Yichen Wu, Fan |
| author_facet | Zhao, Jiahao Nan, Jiayi Wei, Lai Yang, Yichen Wu, Fan |
| contents | Due to the exceptional performance of Large Language Models (LLMs) in diverse downstream tasks,there has been an exponential growth in edge-device requests to cloud-based models.However, the current authentication mechanism using static Bearer Tokens in request headersfails to provide the flexibility and backend control required for edge-device deployments.To address these limitations, we propose Dynaseal,a novel methodology that enables fine-grained backend constraints on model invocations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_08336 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynaseal: A Backend-Controlled LLM API Key Distribution Scheme with Constrained Invocation Parameters Zhao, Jiahao Nan, Jiayi Wei, Lai Yang, Yichen Wu, Fan Cryptography and Security Due to the exceptional performance of Large Language Models (LLMs) in diverse downstream tasks,there has been an exponential growth in edge-device requests to cloud-based models.However, the current authentication mechanism using static Bearer Tokens in request headersfails to provide the flexibility and backend control required for edge-device deployments.To address these limitations, we propose Dynaseal,a novel methodology that enables fine-grained backend constraints on model invocations. |
| title | Dynaseal: A Backend-Controlled LLM API Key Distribution Scheme with Constrained Invocation Parameters |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2501.08336 |