Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.11168 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909687679549440 |
|---|---|
| author | Hackett, William Birch, Lewis Trawicki, Stefan Suri, Neeraj Garraghan, Peter |
| author_facet | Hackett, William Birch, Lewis Trawicki, Stefan Suri, Neeraj Garraghan, Peter |
| contents | Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character injection methods and algorithmic Adversarial Machine Learning (AML) evasion techniques. Through testing against six prominent protection systems, including Microsoft's Azure Prompt Shield and Meta's Prompt Guard, we show that both methods can be used to evade detection while maintaining adversarial utility achieving in some instances up to 100% evasion success. Furthermore, we demonstrate that adversaries can enhance Attack Success Rates (ASR) against black-box targets by leveraging word importance ranking computed by offline white-box models. Our findings reveal vulnerabilities within current LLM protection mechanisms and highlight the need for more robust guardrail systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems Hackett, William Birch, Lewis Trawicki, Stefan Suri, Neeraj Garraghan, Peter Cryptography and Security Artificial Intelligence Machine Learning I.2.7 Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character injection methods and algorithmic Adversarial Machine Learning (AML) evasion techniques. Through testing against six prominent protection systems, including Microsoft's Azure Prompt Shield and Meta's Prompt Guard, we show that both methods can be used to evade detection while maintaining adversarial utility achieving in some instances up to 100% evasion success. Furthermore, we demonstrate that adversaries can enhance Attack Success Rates (ASR) against black-box targets by leveraging word importance ranking computed by offline white-box models. Our findings reveal vulnerabilities within current LLM protection mechanisms and highlight the need for more robust guardrail systems. |
| title | Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems |
| topic | Cryptography and Security Artificial Intelligence Machine Learning I.2.7 |
| url | https://arxiv.org/abs/2504.11168 |