A Cross-Language Investigation into Jailbreak Attacks in Large Language Models. (arXiv:2401.16765v1 [cs.CR])

Large Language Models (LLMs) have become increasingly popular for their
advanced text generation capabilities across various domains. However, like any
software, they face security challenges, including the risk of 'jailbreak'
attacks that manipulate LLMs to produce prohibited content. A particularly
underexplored area is the Multilingual Jailbreak attack, where malicious
questions are translated into various languages to evade safety filters.
Currently, there is a lack of comprehensive empirical studies addressing this
specific threat.

To address this research gap, we conducted an …

advanced area arxiv attack attacks capabilities challenges domains investigation jailbreak language language models large llms popular risk security security challenges software text