paperJune 2025Unreviewed

SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression

Yucheng Li, Surin Ahn, Huiqiang Jiang, Amir H. Abdi, Yuqing Yang, Lili Qiu

arXiv.org

Abstract

Large language models (LLMs) have achieved widespread adoption across numerous applications. However, many LLMs are vulnerable to malicious attacks even after safety alignment. These attacks typically bypass LLMs' safety guardrails by wrapping the original malicious instructions inside adversarial jailbreaks prompts. Previous research has proposed methods such as adversarial training and prompt rephrasing to mitigate these safety vulnerabilities, but these methods often reduce the utility of LLM

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@misc{li2025securitylingua,
  title = {{SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression}},
  author = {Yucheng Li and Surin Ahn and Huiqiang Jiang and Amir H. Abdi and Yuqing Yang and Lili Qiu},
  year = {2025},
  month = jun,
  eprint = {2506.12707},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2506.12707},
  url = {https://www.semanticscholar.org/paper/886194f65d0c2a0b56458d8ba2cd96bd69a97f6a}
}