Hi~ I am Peng Ding (丁鹏), a Ph.D. candidate at the School of Computer Science, Nanjing University, supervised by Prof. Shujian Huang.

My current research interests focus on the safety of large language models (LLMs), including jailbreak attacks, defense mechanisms, and interpretability. I am also interested in other topics related to LLMs, such as reasoning and reinforcement learning.

Now, I am a research intern at Meituan. Please feel free to contact me via email!

🔥 News

• 2025.05:  🎉🎉 Our paper “Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement” is accepted by ACL 2025 (Findings).
• 2024.07:  🎉🎉 Our paper “Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs” is accepted by MM 2024.
• 2024.03:  🎉🎉 Our paper “A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily” is accepted by NAACL 2024 (Oral).

📝 Publications

ACL 2025 (Findings)

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement

Peng Ding, Jun Kuang, Zongyu Wang, Xuezhi Cao, Xunliang Cai, Jiajun Chen, Shujian Huang

💻 [Code]: Link

📄 [Paper]: Link

MM 2024

Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs

Peng Ding^*, Jingyu Wu^*, Jun Kuang, Dan Ma, Xuezhi Cao, Xunliang Cai, Shi Chen, Jiajun Chen, Shujian Huang

💻 [Code]: Link

📄 [Paper]: Link

NAACL 2024 (Oral)

A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao, Yunsen Xian, Jiajun Chen, Shujian Huang

💻 [Code]: Link

📄 [Paper]: Link

📖 Educations

• 2019.06 - now, Ph.D. candidate at the School of Computer Science, Nanjing University.
• 2016.09 - 2019.06, Master’s degree, School of Information Science and Engineering, Yunnan University.

💻 Internships

• 2023.08 - now, Meituan Inc., Shanghai, China.

🎖 Honors and Awards

• 2018.10 Yunnan Provincial Government Scholarship.