2025
“Finding and Reactivating Post-Trained LLMs’ Hidden Safety Mechanisms
Mingjie Li, Wai-man Si, Michael Backes, Yang Zhang, Yisen Wang; NeurIPS 2025“Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency
Yukun Jiang, Mingjie Li, Michael Backes, Yang Zhang; NeurIPS 2025“Salora: Safety-alignment preserved low-rank adaptation
Mingjie Li, Wai-man Si, Michael Backes, Yang Zhang, Yisen Wang; ICLR 2025pdf projectpage
“Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data
Atilla Akkus* and Masoud Poorghaffar Aghdam*; Mingjie Li*(Co-first Author), Junjie Chu, Michael Backes, and Yang Zhang, Sinem Sav; USENIX Security 2025pdf projectpage
“JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
Junjie Chu, Mingjie Li, Ziqing Yang, Ye Leng, Chenhao Lin, Chao Shen, Michael Backes, Yun Shen, Yang Zhang; ArXivpdf projectpage
“Excessive Reasoning Attack on Reasoning LLMs
Wai-man Si, Mingjie Li, Michael Backes, Yang Zhang; ArXivpdf
“Excessive Reasoning Attack on Reasoning LLMs
Ang Li, Yichuan Mo, Mingjie Li, Yifei Wang, Yisen Wang; ArXivpdf
2024
“ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation Models
Zeyang Sha, Yicong Tan, Mingjie Li, Michael Backes, Yang Zhang; CCS 2024pdf code
“PID: Prompt-Independent Data Protection Against Latent Diffusion Models
Ang Li, Yichuan Mo, Mingjie Li, Yisen Wang; ICML 2024pdf
“TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
Yichuan Mo, Hui Huang, Mingjie Li, Yisen Wang; ICML 2024pdf code
2023
GEQ: Gaussian Kernel Inspired Equilibrium Models
Mingjie Li, Yisen Wang, Zhouchen Lin; NeurIPS 2023pdf
Pareto Adversarial Robustness: Balancing Spatial Robustness and Sensitivity-based Robustness
Ke Sun, Mingjie Li, Zhouchen Lin; SCIENCE CHINA Information Sciences 2025pdf
Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States
Mingjie Li, Yifei Wang, Yisen Wang, Zhouchen Lin; ICLR 2023pdf
2022
G^2CN: Graph Gaussian Convolution Networks with Concentrated Graph Filters
Mingjie Li, Xiaojun Guo, Yifei Wang, Yisen Wang, Zhouchen Lin; ICML 2022pdf code
Cerdeq: Certifiable deep equilibrium model
Mingjie Li, Yisen Wang, ZhouchenLin; ICML 2022pdf
Optimization inspired multi-branch equilibrium models
Mingjie Li, Yisen Wang, Xingyu Xie, Zhouchen Lin; ICLR 2022pdf
2020
Implicit euler skip connections: Enhancing adversarial robustness via numerical stability
Mingjie Li, Lingshen He, Zhouchen Lin ICML 2020pdf code
2018
Deep Convolutional Neural Networks with Merge-and-Run Mappings
Liming Zhao, Mingjie Li, Depu Meng, Xi Li, Zhaoxiang Zhang, Yueting Zhuang, Zhuowen Tu, Jingdong Wang IJCAI 2018pdf
Igcv3: Interleaved low-rank group convolutions for efficient deep neural networks
Ke Sun, Mingjie Li, Dong Liu, Jingdong Wang BMVC 2018pdf
