5 papers
BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning
Xuan Luo, Yue Wang, Geng Tu +2
In this work, we propose BAIT (Boundary-Aware Iterative Trap), a three-step jailbreak framework that approaches malicious goals through internal disclosure. BAIT first asks the mod…
Speech-Omni-Lite: Portable Speech Interfaces for Vision-Language Models
Dehua Tao, Xuan Luo, Daxin Tan +5
While large-scale omni-models have demonstrated impressive capabilities across various modalities, their strong performance heavily relies on massive multimodal data and incurs sub…
Evaluating Proactive Risk Awareness of Large Language Models
Xuan Luo, Yubin Chen, Zhiyu Hou +4
As large language models (LLMs) are increasingly embedded in everyday decision-making, their safety responsibilities extend beyond reacting to explicit harmful intent toward antici…
A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness
Xuan Luo, Yue Wang, Zefeng He +3
This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can reliably elicit harmful responses…
AEQ-Bench: Measuring Empathy of Omni-Modal Large Models
Xuan Luo, Lewei Yao, Libo Zhao +6
While the automatic evaluation of omni-modal large models (OLMs) is essential, assessing empathy remains a significant challenge due to its inherent affectivity. To investigate thi…