Papers by Haichang Gao
The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have remarkable capabilities, but their security implications have been overlooked. |
| Approach: | They propose a “jailbreak function” attack method that exploits alignment discrepancies, user coercion, and the absence of rigorous safety filters. |
| Outcome: | The proposed attack exploits alignment discrepancies, user coercion, and the absence of rigorous safety filters on six state-of-the-art LLMs. |