LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models

Abstract

While safety-aligned large language models (LLMs) are increasingly used as the cornerstone for powerful systems such as multi-agent frameworks to solve complex real-world problems, they still suffer from potential adversarial queries, such as jailbreak attacks, which attempt to induce harmful content. Researching attack methods allows us to better understand the limitations of LLM and make trade-offs between helpfulness and safety. However, existing jailbreak attacks are primarily based on opaqu

Categories

Framework mappings

Suggested from the entry's categories.

@misc{yu2024llmvirus,
  title = {{LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models}},
  author = {Miao Yu and Junfeng Fang and Yingjie Zhou and Xing Fan and Kun Wang and Shirui Pan and Qingsong Wen},
  year = {2024},
  month = dec,
  eprint = {2501.00055},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2501.00055},
  url = {https://www.semanticscholar.org/paper/0f2721b409db7793f70b8990858709108ac67633}
}