Xiang, Zhen
- ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
2024/02/19 by Fengqing Jiang, Jiang, Fengqing, Zhangchen Xu +11 · 11 voices · 54 citations
Computer Science · #Digital and Cyber Forensics #Digital Rights Management and Security #Law, AI, and Intellectual Property
- AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
2024/07/17 by Chen, Zhaorun, Xiang, Zhen, Xiao, Chaowei +2 · 73 citations
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG)
- Evaluation of OpenAI o1: Opportunities and Challenges of AGI
2024/09/27 by Tianyang Zhong, Zhengliang Liu, Zhong, Tianyang +158 · 1 voice · 19 citations
Computer Science · #Image Retrieval and Classification Techniques #cs.CL
- GuardAgent: Safeguard LLM Agents by a Guard Agent via Knowledge-Enabled Reasoning
2024/06/13 by Zhen Xiang, Xiang, Zhen, Linzhi Zheng +21 · 36 citations
Computer Science · Engineering · Social Sciences · #Access Control and Trust #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection #Smart Grid Security and Resilience
- BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
2024/01/20 by Zhen Xiang, Xiang, Zhen, Fengqing Jiang +9 · 15 citations
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #Artificial Intelligence in Healthcare and Education #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Topic Modeling
- MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic
2022/05/13 by Hang Wang, Wang, Hang, Zhen Xiang +5 · 10 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
2025/02/17 by Fengqing Jiang, Jiang, Fengqing, Zhangchen Xu +13 · 28 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling
- Unveiling Privacy Risks in LLM Agent Memory
2025/02/17 by Bo Wang, Wang, Bo, Weiyi He +11 · 20 citations
Computer Science · #Cloud Data Security Solutions #Security and Verification in Computing #Privacy-Preserving Technologies in Data
- SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
2024/12/17 by Yin, Sheng, Pang, Xianghe, Ding, Yuanzhuo +7 · 17 citations
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Robotics (cs.RO)
- Physical Backdoor Attack can Jeopardize Driving with Vision-Large-Language Models
2024/04/19 by Zhenyang Ni, Ni, Zhenyang, Rui Ye +9 · 9 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Autonomous Vehicle Technology and Safety
- Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review
2024/12/02 by Ye, Rui, Pang, Xianghe, Chai, Jingyi +6 · 10 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Machine Learning (cs.LG)
- How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
2025/05/21 by Xiong, Zidi, Lin, Yuping, Xie, Wenya +5 · 16 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences
- Memory Injection Attacks on LLM Agents via Query-Only Interaction
2025/03/05 by Dong, Shen, Xu, Shaochen, He, Pengfei +5 · 9 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- A Backdoor Attack against 3D Point Cloud Classifiers
2021/04/12 by Xiang, Zhen, Miller, David J., Chen, Siheng +2 · 2 citations
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
2025/04/27 by Luo, Weidi, Lu, Tianyu, Zhang, Qiming +8 · 8 citations
#Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
2025/03/19 by Chejian Xu, Jiawei Zhang, Xu, Chejian +44 · 3 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Multi-Agent Systems and Negotiation
- Malicious Agent Detection for Robust Multi-Agent Collaborative Perception
2023/10/18 by Zhao, Yangheng, Xiang, Zhen, Yin, Sheng +3 · 1 citation
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios
2022/01/20 by Zhen Xiang, David J. Miller, Xiang, Zhen +3 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection
- CBD: A Certified Backdoor Detector Based on Local Dominant Probability
2023/10/26 by Xiang, Zhen, Xiong, Zidi, Li, Bo · 1 citation
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
2025/06/02 by He, Pengfei, Xing, Yue, Dong, Shen +7 · 4 citations
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences
- SoSBench: Benchmarking Safety Alignment on Six Scientific Domains
2025/05/27 by Fengqing Jiang, Jiang, Fengqing, Feiyue Ma +14 · 2 citations
Health Professions · Decision Sciences · Engineering · #Occupational Health and Safety Research #Risk and Safety Analysis #Safety Systems Engineering in Autonomy
- Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios
2024/11/16 by Xu, Shaochen, Zhou, Yifan, Liu, Zhengliang +19 · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences
- Detection of Backdoors in Trained Classifiers Without Access to the Training Set
2019/08/27 by Xiang, Zhen, Miller, David J., Kesidis, George · 1 citation
#Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Data Free Backdoor Attacks
2024/12/09 by Bochuan Cao, Cao, Bochuan, Jinyuan Jia +13 · 1 citation
Computer Science · #Network Security and Intrusion Detection #Advanced Malware Detection Techniques #Information and Cyber Security
- Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
2025/07/25 by Lu, Haoran, Fang, Luyang, Zhang, Ruidong +47 · 3 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Multi-Faceted Studies on Data Poisoning can Advance LLM Development
2025/02/20 by Pengfei He, Yue Xing, He, Pengfei +7 · 1 citation
Decision Sciences · #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Scientific Computing and Data Management
- Large Language Model Empowered Privacy-Protected Framework for PHI Annotation in Clinical Notes
2025/04/22 by Guanchen Wu, Linzhi Zheng, Wu, Guanchen +16 · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare #Privacy-Preserving Technologies in Data #Topic Modeling