System Prompt Extraction Attacks and Defenses in Large Language Models
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_ | 1866916766949572608 |
|---|---|
| author | Das, Badhan Chandra Amini, M. Hadi Wu, Yanzhao |
| author_facet | Das, Badhan Chandra Amini, M. Hadi Wu, Yanzhao |
| contents | The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that LLM system prompts are highly susceptible to extraction attacks through meticulously designed queries, raising significant privacy and security concerns. Despite the growing threat, there is a lack of systematic studies of system prompt extraction attacks and defenses. In this paper, we present a comprehensive framework, SPE-LLM, to systematically evaluate System Prompt Extraction attacks and defenses in LLMs. First, we design a set of novel adversarial queries that effectively extract system prompts in state-of-the-art (SOTA) LLMs, demonstrating the severe risks of LLM system prompt extraction attacks. Second, we propose three defense techniques to mitigate system prompt extraction attacks in LLMs, providing practical solutions for secure LLM deployments. Third, we introduce a set of rigorous evaluation metrics to accurately quantify the severity of system prompt extraction attacks in LLMs and conduct comprehensive experiments across multiple benchmark datasets, which validates the efficacy of our proposed SPE-LLM framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23817 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | System Prompt Extraction Attacks and Defenses in Large Language Models Das, Badhan Chandra Amini, M. Hadi Wu, Yanzhao Cryptography and Security The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become an emerging attack target. Recent studies have shown that LLM system prompts are highly susceptible to extraction attacks through meticulously designed queries, raising significant privacy and security concerns. Despite the growing threat, there is a lack of systematic studies of system prompt extraction attacks and defenses. In this paper, we present a comprehensive framework, SPE-LLM, to systematically evaluate System Prompt Extraction attacks and defenses in LLMs. First, we design a set of novel adversarial queries that effectively extract system prompts in state-of-the-art (SOTA) LLMs, demonstrating the severe risks of LLM system prompt extraction attacks. Second, we propose three defense techniques to mitigate system prompt extraction attacks in LLMs, providing practical solutions for secure LLM deployments. Third, we introduce a set of rigorous evaluation metrics to accurately quantify the severity of system prompt extraction attacks in LLMs and conduct comprehensive experiments across multiple benchmark datasets, which validates the efficacy of our proposed SPE-LLM framework. |
| title | System Prompt Extraction Attacks and Defenses in Large Language Models |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2505.23817 |