Bio
Profile
Exploring secure and trustworthy AI, from deepfake detection to robust large language models.
Based in Qingdao, China. 2nd-year Ph.D., School of Cyber Science and Technology at Shandong University.
- Trustworthy Machine Learning
Researching safety, robustness, and privacy across generative models and LLM agents.
- Deepfake Forensics
Building attacks and defenses for facial forgery detection in practical pipelines.
- Secure LLM Systems
Designing evaluation frameworks that expose risk interactions and support safer deployments.
Updates
Latest News
Investigating unintended risk interactions introduced by LLM defenses.
Read moreBlack-box traceability based on model family error space.
Read moreJoint research project on LLM security testing and risk assessment with Topsec.
Read moreSafety patch for mitigating unsafe content in text-to-image generation models.
Read moreAutomated framework for jailbreaking text-to-image generation models.
Read moreRecognized for thesis on robustness research for deepfake detection.
Read moreSelected Works