5 papers
Many-Turn Jailbreaking
Xianjun Yang, Liqiang Xiao, Shiyang Li +5
Current jailbreaking work on large language models (LLMs) aims to elicit unsafe outputs from given prompts. However, it only focuses on single-turn jailbreaking targeting one speci…
Weak-to-Strong Jailbreaking on Large Language Models
Xuandong Zhao, Xianjun Yang, Tianyu Pang +4
Large language models (LLMs) are vulnerable to jailbreak attacks - resulting in harmful, unethical, or biased text generations. However, existing jailbreaking methods are computati…
MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents
Kaijie Zhu, Xianjun Yang, Jindong Wang +2
Recent research has explored that LLM agents are vulnerable to indirect prompt injection (IPI) attacks, where malicious tasks embedded in tool-retrieved information can redirect th…
CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
Mian Zhang, Xianjun Yang, Xinlu Zhang +6
There is a significant gap between patient needs and available mental health support today. In this paper, we aim to thoroughly examine the potential of using Large Language Models…
Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning
Xinlu Zhang, Zhiyu Zoey Chen, Xi Ye +4
Instruction Fine-Tuning (IFT) significantly enhances the zero-shot capabilities of pretrained Large Language Models (LLMs). While coding data is known to boost LLM reasoning abilit…