Ranjie Duan - RankMe

48 papers A* 12A 1Journal 34Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5. CoRR Xingjun Ma, Yixu Wang, Hengyuan Xu, Yutao Wu, Yifan Ding, Yunhan Zhao, Zilong Wang, Jiabin Hua, Ming Wen, Jianan Liu, Ranjie Duan, Yifeng Gao, Yingshui Tan, Yunhao Chen, Hui Xue, Xin Wang, Wei Cheng, Jingjing Chen, Zuxuan Wu, Bo Li, Yu-Gang Jiang
2026	J	`jnl`	Improving Safety Alignment via Balanced Direct Preference Optimization. CoRR Shiji Zhao, Mengyang Wang, Shukun Xiong, Fangzhou Chen, Qihui Zhu, Shouwei Ruan, Yisong Xiao, Ranjie Duan, Xun Chen, Xingxing Wei
2026	J	`jnl`	Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling. CoRR Shiji Zhao, Shukun Xiong, Maoxun Yuan, Yao Huang, Ranjie Duan, Qing Guo, Jiansheng Chen, Haibin Duan, Xingxing Wei
2026	J	`jnl`	Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search. CoRR Xun Huang, Simeng Qin, Xiaoshuang Jia, Ranjie Duan, Huanqian Yan, Zhitao Zeng, Fei Yang, Yang Liu, Xiaojun Jia
2026	J	`jnl`	Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models. CoRR Xuan Ding, Pengyu Tong, Ranjie Duan, Yunjian Zhang, Rui Sun, Yao Zhu
2026	J	`jnl`	YuFeng-XGuard: A Reasoning-Centric, Interpretable, and Flexible Guardrail Model for Large Language Models. CoRR Junyu Lin, Meizhen Liu, Xiufeng Huang, Jinfeng Li, Haiwen Hong, Xiaohan Yuan, Yuefeng Chen, Longtao Huang, Hui Xue, Ranjie Duan, Zhikai Chen, Yuchuan Fu, Defeng Li, Lingyao Gao, Yitong Yang
2025	—	`conf`	DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models. NAACL (Long Papers) Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Pei Wang, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu
2025	J	`jnl`	DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models. CoRR Jianyu Liu, Hangyu Guo, Ranjie Duan, Xingyuan Bu, Yancheng He, Shilong Li, Hui Huang, Jiaheng Liu, Yucheng Wang, Chenchen Jing, Xingwei Qu, Xiao Zhang, Yingshui Tan, Yanan Wu, Jihao Gu, Yangguang Li, Jianke Zhu
2025	J	`jnl`	Energy-Driven Steering: Reducing False Refusals in Large Language Models. CoRR Eric Hanchen Jiang, Weixuan Ou, Run Liu, Shengyuan Pang, Guancheng Wan, Ranjie Duan, Wei Dong, Kai-Wei Chang, Xiaofeng Wang, Ying Nian Wu, Xinfeng Li
2025	J	`jnl`	Enhancing Adversarial Robustness of Vision Language Models via Adversarial Mixture Prompt Tuning. CoRR Shiji Zhao, Qihui Zhu, Shukun Xiong, Shouwei Ruan, Yize Fan, Ranjie Duan, Qing Guo, Xingxing Wei
2025	J	`jnl`	Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency. CoRR Shiji Zhao, Ranjie Duan, Fengxiang Wang, Chi Chen, Caixin Kang, Jialing Tao, Yuefeng Chen, Hui Xue, Xingxing Wei
2025	A*	`conf`	Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink. USENIX Security Symposium Yining Wang, Mi Zhang, Junjie Sun, Chenyue Wang, Min Yang, Hui Xue, Jialing Tao, Ranjie Duan, Jiexi Liu
2025	J	`jnl`	Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink. CoRR Yining Wang, Mi Zhang, Junjie Sun, Chenyue Wang, Min Yang, Hui Xue, Jialing Tao, Ranjie Duan, Jiexi Liu
2025	A*	`conf`	NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation. ACM Multimedia Yitong Sun, Yao Huang, Ruochen Zhang, Huanran Chen, Shouwei Ruan, Ranjie Duan, Xingxing Wei
2025	J	`jnl`	NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation. CoRR Yitong Sun, Yao Huang, Ruochen Zhang, Huanran Chen, Shouwei Ruan, Ranjie Duan, Xingxing Wei
2025	J	`jnl`	OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation. CoRR Xiaojun Jia, Jie Liao, Qi Guo, Teng Ma, Simeng Qin, Ranjie Duan, Tianlin Li, Yihao Huang, Zhitao Zeng, Dongxian Wu, Yiming Li, Wenqi Ren, Xiaochun Cao, Yang Liu
2025	J	`jnl`	Oyster-I: Beyond Refusal - Constructive Safety Alignment for Responsible Language Models. CoRR Ranjie Duan, Jiexi Liu, Xiaojun Jia, Shiji Zhao, Ruoxi Cheng, Fengxiang Wang, Cheng Wei, Yong Xie, Chang Liu, Defeng Li, Yinpeng Dong, Yichi Zhang, Yuefeng Chen, Chongwen Wang, Xingjun Ma, Xingxing Wei, Yang Liu, Hang Su, Jun Zhu, Xinfeng Li, Yitong Sun, Jie Zhang, Jinzhao Hu, Sha Xu, Wenchao Yang, Yitong Yang, Xingyao Zhang, Yingshui Tan, Jialing Tao, Hui Xue
2025	A*	`conf`	PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization. EMNLP Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Ranjie Duan, Xiaoshuang Jia, Shaowei Yuan, Simeng Qin, Zhiqiang Wang, Xiaojun Jia
2025	J	`jnl`	RobustPrompt: Learning to defend against adversarial attacks with adaptive visual prompts. Pattern Recognit. Lett. Chang Liu, Wenzhao Xiang, Yinpeng Dong, Xingxing Zhang, Liyuan Wang, Ranjie Duan, Shibao Zheng, Hang Su
2025	A*	`conf`	STAIR: Improving Safety Alignment with Introspective Reasoning. ICML Yichi Zhang, Siyuan Zhang, Yao Huang, Zeyu Xia, Zhengwei Fang, Xiao Yang, Ranjie Duan, Dong Yan, Yinpeng Dong, Jun Zhu
2025	J	`jnl`	STAIR: Improving Safety Alignment with Introspective Reasoning. CoRR Yichi Zhang, Siyuan Zhang, Yao Huang, Zeyu Xia, Zhengwei Fang, Xiao Yang, Ranjie Duan, Dong Yan, Yinpeng Dong, Jun Zhu
2025	J	`jnl`	SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG. CoRR Xiaonan Si, Meilin Zhu, Simeng Qin, Lijia Yu, Lijun Zhang, Shuaitong Liu, Xinfeng Li, Ranjie Duan, Yang Liu, Xiaojun Jia
2025	J	`jnl`	Strata-Sword: A Hierarchical Safety Evaluation towards LLMs based on Reasoning Complexity of Jailbreak Instructions. CoRR Shiji Zhao, Ranjie Duan, Jiexi Liu, Xiaojun Jia, Fengxiang Wang, Cheng Wei, Ruoxi Cheng, Yong Xie, Chang Liu, Qing Guo, Jialing Tao, Hui Xue, Xingxing Wei
2025	A*	`conf`	The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework. ACM Multimedia Feiran Liu, Yuzhe Zhang, Xinyi Huang, Yinan Peng, Xinfeng Li, Lixu Wang, Yutong Shen, Ranjie Duan, Simeng Qin, Xiaojun Jia, Qingsong Wen, Wei Dong
2025	J	`jnl`	The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework. CoRR Feiran Liu, Yuzhe Zhang, Xinyi Huang, Yinan Peng, Xinfeng Li, Lixu Wang, Yutong Shen, Ranjie Duan, Simeng Qin, Xiaojun Jia, Qingsong Wen, Wei Dong
2025	J	`jnl`	Towards Class-wise Fair Adversarial Training via Anti-Bias Soft Label Distillation. CoRR Shiji Zhao, Chi Chen, Ranjie Duan, Xizhe Wang, Xingxing Wei
2025	J	`jnl`	Towards Safe Reasoning in Large Reasoning Models via Corrective Intervention. CoRR Yichi Zhang, Yue Ding, Jingwen Yang, Tianwei Luo, Dongbai Li, Ranjie Duan, Qiang Liu, Hang Su, Yinpeng Dong, Jun Zhu
2025	J	`jnl`	VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack. CoRR Shiji Zhao, Shukun Xiong, Yao Huang, Yan Jin, Zhenyu Wu, Jiyang Guan, Ranjie Duan, Jialing Tao, Hui Xue, Xingxing Wei
2024	J	`jnl`	Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models. CoRR Ma Teng, Xiaojun Jia, Ranjie Duan, Xinfeng Li, Yihao Huang, Zhixuan Chu, Yang Liu, Wenqi Ren
2024	A*	`conf`	Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation. NeurIPS Shiji Zhao, Ranjie Duan, Xizhe Wang, Xingxing Wei
2024	J	`jnl`	MRJ-Agent: An Effective Jailbreak Agent for Multi-Round Dialogue. CoRR Fengxiang Wang, Ranjie Duan, Peng Xiao, Xiaojun Jia, Yuefeng Chen, Chongwen Wang, Jialing Tao, Hang Su, Jun Zhu, Hui Xue
2024	J	`jnl`	PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization. CoRR Ruoxi Cheng, Yizhong Ding, Shuirong Cao, Ranjie Duan, Xiaoshuang Jia, Shaowei Yuan, Zhiqiang Wang, Xiaojun Jia
2024	J	`jnl`	RT-Attack: Jailbreaking Text-to-Image Models via Random Token. CoRR Sensen Gao, Xiaojun Jia, Yihao Huang, Ranjie Duan, Jindong Gu, Yang Liu, Qing Guo
2024	J	`jnl`	Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging. IEEE Trans. Inf. Forensics Secur. Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao, Ranjie Duan, Jindong Gu, Rong Zhang, Hui Xue, Yang Liu, Xiaochun Cao
2023	A*	`conf`	Inequality phenomenon in l ICLR Ranjie Duan, Yuefeng Chen, Yao Zhu, Xiaojun Jia, Rong Zhang, Hui Xue
2023	J	`jnl`	Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging. CoRR Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao, Ranjie Duan, Jindong Gu, Rong Zhang, Hui Xue, Xiaochun Cao
2023	A	`conf`	Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training. INTERSPEECH Gege Qi, Yuefeng Chen, Xiaofeng Mao, Xiaojun Jia, Ranjie Duan, Rong Zhang, Hui Xue
2023	J	`jnl`	Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training. CoRR Gege Qi, Yuefeng Chen, Xiaofeng Mao, Xiaojun Jia, Ranjie Duan, Rong Zhang, Hui Xue
2022	A*	`conf`	Enhance the Visual Representation via Discrete Adversarial Training. NeurIPS Xiaofeng Mao, Yuefeng Chen, Ranjie Duan, Yao Zhu, Gege Qi, Shaokai Ye, Xiaodan Li, Rong Zhang, Hui Xue
2022	J	`jnl`	Enhance the Visual Representation via Discrete Adversarial Training. CoRR Xiaofeng Mao, Yuefeng Chen, Ranjie Duan, Yao Zhu, Gege Qi, Shaokai Ye, Xiaodan Li, Rong Zhang, Hui Xue
2022	A*	`conf`	Towards Robust Vision Transformer. CVPR Xiaofeng Mao, Gege Qi, Yuefeng Chen, Xiaodan Li, Ranjie Duan, Shaokai Ye, Yuan He, Hui Xue
2021	A*	`conf`	AdvDrop: Adversarial Attack to DNNs by Dropping Information. ICCV Ranjie Duan, Yuefeng Chen, Dantong Niu, Yun Yang, A. K. Qin, Yuan He
2021	J	`jnl`	AdvDrop: Adversarial Attack to DNNs by Dropping Information. CoRR Ranjie Duan, Yuefeng Chen, Dantong Niu, Yun Yang, A. K. Qin, Yuan He
2021	A*	`conf`	Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink. CVPR Ranjie Duan, Xiaofeng Mao, A. K. Qin, Yuefeng Chen, Shaokai Ye, Yuan He, Yun Yang
2021	J	`jnl`	Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink. CoRR Ranjie Duan, Xiaofeng Mao, A. K. Qin, Yun Yang, Yuefeng Chen, Shaokai Ye, Yuan He
2021	J	`jnl`	Towards Robust Vision Transformer. CoRR Xiaofeng Mao, Gege Qi, Yuefeng Chen, Xiaodan Li, Ranjie Duan, Shaokai Ye, Yuan He, Hui Xue
2020	A*	`conf`	Adversarial Camouflage: Hiding Physical-World Attacks With Natural Styles. CVPR Ranjie Duan, Xingjun Ma, Yisen Wang, James Bailey, A. K. Qin, Yun Yang
2020	J	`jnl`	Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles. CoRR Ranjie Duan, Xingjun Ma, Yisen Wang, James Bailey, A. K. Qin, Yun Yang