Tianrong Zhang

WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response

2024 · arXiv (Cornell University)

The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to jailbreaking attacks, which leads to …