| 2026 | ACL | BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents. | Yunhao Feng, Yige Li, Yutao Wu, Yingshui Tan, Yanming Guo, Yifan Ding, Kun Zhai, Xingjun Ma, Yu-Gang Jiang |
| 2026 | EACL | Unleashing the Unseen: Harnessing Benign Datasets for Jailbreaking Large Language Models. | Wei Zhao, Zhe Li, Yige Li, Jun Sun |
| 2026 | NDSS | Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security. | Wei Zhao, Zhe Li, Yige Li, Jun Sun |
| 2025 | AAAI | Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models. | Peihai Jiang, Xixiang Lyu, Yige Li, Jing Ma |
| 2025 | CVPR | Anyattack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models. | Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Yunhao Chen, Jitao Sang, Dit-Yan Yeung |
| 2025 | EMNLP | Do Influence Functions Work on Large Language Models? | Zhe Li, Wei Zhao, Yige Li, Jun Sun |
| 2025 | EMNLP | Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs. | Wei Zhao, Zhe Li, Yige Li, Jun Sun |
| 2025 | ICLR | Detecting Backdoor Samples in Contrastive Language Image Pretraining. | Hanxun Huang, Sarah Monazam Erfani, Yige Li, Xingjun Ma, James Bailey |
| 2025 | ICLR | BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks. | Yunhan Zhao, Xiang Zheng, Lin Luo, Yige Li, Xingjun Ma, Yu-Gang Jiang |
| 2025 | ICML | X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP. | Hanxun Huang, Sarah Monazam Erfani, Yige Li, Xingjun Ma, James Bailey |
| 2025 | ICML | CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization. | Nay Myat Min, Long H. Pham, Yige Li, Jun Sun |
| 2024 | EMNLP | Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing. | Wei Zhao, Zhe Li, Yige Li, Ye Zhang, Jun Sun |
| 2023 | ICML | Reconstructive Neuron Pruning for Backdoor Defense. | Yige Li, Xixiang Lyu, Xingjun Ma, Nodens Koren, Lingjuan Lyu, Bo Li, Yu-Gang Jiang |
| 2023 | ISCC | Lightweight Video Frame Interpolation Based on Bidirectional Attention Module. | Yige Li, Han Yang |
| 2021 | ICLR | Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks. | Yige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu, Bo Li, Xingjun Ma |