Covert Prompt Transmission for Secure Large Language Model Services
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909597635182592 |
|---|---|
| author | Zhang, Ruichen Liu, Yinqiu Tang, Shunpu Wang, Jiacheng Niyato, Dusit Sun, Geng Li, Yonghui Sun, Sumei |
| author_facet | Zhang, Ruichen Liu, Yinqiu Tang, Shunpu Wang, Jiacheng Niyato, Dusit Sun, Geng Li, Yonghui Sun, Sumei |
| contents | This paper investigates covert prompt transmission for secure and efficient large language model (LLM) services over wireless networks. We formulate a latency minimization problem under fidelity and detectability constraints to ensure confidential and covert communication by jointly optimizing the transmit power and prompt compression ratio. To solve this problem, we first propose a prompt compression and encryption (PCAE) framework, performing surprisal-guided compression followed by lightweight permutation-based encryption. Specifically, PCAE employs a locally deployed small language model (SLM) to estimate token-level surprisal scores, selectively retaining semantically critical tokens while discarding redundant ones. This significantly reduces computational overhead and transmission duration. To further enhance covert wireless transmission, we then develop a group-based proximal policy optimization (GPPO) method that samples multiple candidate actions for each state, selecting the optimal one within each group and incorporating a Kullback-Leibler (KL) divergence penalty to improve policy stability and exploration. Simulation results show that PCAE achieves comparable LLM response fidelity to baseline methods while reducing preprocessing latency by over five orders of magnitude, enabling real-time edge deployment. We further validate PCAE effectiveness across diverse LLM backbones, including DeepSeek-32B, Qwen-32B, and their smaller variants. Moreover, GPPO reduces covert transmission latency by up to 38.6\% compared to existing reinforcement learning strategies, with further analysis showing that increased transmit power provides additional latency benefits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_21311 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Covert Prompt Transmission for Secure Large Language Model Services Zhang, Ruichen Liu, Yinqiu Tang, Shunpu Wang, Jiacheng Niyato, Dusit Sun, Geng Li, Yonghui Sun, Sumei Networking and Internet Architecture This paper investigates covert prompt transmission for secure and efficient large language model (LLM) services over wireless networks. We formulate a latency minimization problem under fidelity and detectability constraints to ensure confidential and covert communication by jointly optimizing the transmit power and prompt compression ratio. To solve this problem, we first propose a prompt compression and encryption (PCAE) framework, performing surprisal-guided compression followed by lightweight permutation-based encryption. Specifically, PCAE employs a locally deployed small language model (SLM) to estimate token-level surprisal scores, selectively retaining semantically critical tokens while discarding redundant ones. This significantly reduces computational overhead and transmission duration. To further enhance covert wireless transmission, we then develop a group-based proximal policy optimization (GPPO) method that samples multiple candidate actions for each state, selecting the optimal one within each group and incorporating a Kullback-Leibler (KL) divergence penalty to improve policy stability and exploration. Simulation results show that PCAE achieves comparable LLM response fidelity to baseline methods while reducing preprocessing latency by over five orders of magnitude, enabling real-time edge deployment. We further validate PCAE effectiveness across diverse LLM backbones, including DeepSeek-32B, Qwen-32B, and their smaller variants. Moreover, GPPO reduces covert transmission latency by up to 38.6\% compared to existing reinforcement learning strategies, with further analysis showing that increased transmit power provides additional latency benefits. |
| title | Covert Prompt Transmission for Secure Large Language Model Services |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2504.21311 |