5 papers
Diversity Helps Jailbreak Large Language Models
Weiliang Zhao, Daniel Ben-Levi, Wei Hao +2
We have uncovered a powerful jailbreak technique that leverages large language models' ability to diverge from prior context, enabling them to bypass safety constraints and generat…
LAVID: An Agentic LVLM Framework for Diffusion-Generated Video Detection
Qingyuan Liu, Yun-Yun Tsai, Ruijian Zha +4
The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works of AI-genera…
Learning to Rewrite: Generalized LLM-Generated Text Detection
Ran Li, Wei Hao, Weiliang Zhao +2
Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial…
I Can Hear You: Selective Robust Training for Deepfake Audio Detection
Zirui Zhang, Wei Hao, Aroon Sankoh +4
Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we…
SPIN: Self-Supervised Prompt INjection
Leon Zhou, Junfeng Yang, Chengzhi Mao
Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbr…