Ranjie Duan
- STAIR: Improving Safety Alignment with Introspective Reasoning
2025/02/04 by Yichi Zhang, Zhang, Yichi, Siyuan Zhang +14 · 28 citations
Computer Science · Decision Sciences · Engineering · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Risk and Safety Analysis #Safety Systems Engineering in Autonomy #Software Reliability and Analysis Research
- Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink
2021/03/11 by Ranjie Duan, Xiaofeng Mao, Duan, Ranjie +11 · 4 citations
Computer Science · Physics and Astronomy · Engineering · #Adversarial Robustness in Machine Learning #Advanced Optical Sensing Technologies #Integrated Circuits and Semiconductor Failure Analysis
- Enhance the Visual Representation via Discrete Adversarial Training
2022/09/16 by Xiaofeng Mao, Mao, Xiaofeng, Yuefeng Chen +15 · 2 citations
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Image Processing Techniques and Applications
- HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
2024/08/25 by Sensen Gao, Gao, Sensen, Xiaojun Jia +12 · 3 citations
Computer Science · #Advanced Steganography and Watermarking Techniques #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #Digital Media Forensic Detection #Digital and Cyber Forensics #FOS: Computer and information sciences
- Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
2026/02/26 by Xun Huang, Simeng Qin, Xiaoshuang Jia +6 · 1 voice
Computer Science · #cs.AI #cs.CR
- DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
2025/04/25 by Jianyu Liu, Liu, Jianyu, Guo, Hangyu +30 · 3 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #Computer Vision and Pattern Recognition (cs.CV) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Topic Modeling