Xiangyu Qi - RankMe

39 papers A* 13Journal 23Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition. CoRR Mateusz Dziemian, Maxwell Lin, Xiaohan Fu, Micha Nowak, Nick Winter, Eliot Krzysztof Jones, Andy Zou, Lama Ahmad, Kamalika Chaudhuri, Sahana Chennabasappa, Xander Davies, Lauren Deason, Benjamin L. Edelman, Tanner Emek, Ivan Evtimov, Jim Gust, Maia Hamin, Kat He, Klaudia Krawiecka, Riccardo Patana, Neil Perry, Troy Peterson, Xiangyu Qi, Javier Rando, Zifan Wang, Zihan Wang, Spencer Whitman, Eric Winsor, Arman Zharmagambetov, Matt Fredrikson, Zico Kolter
2025	—	`conf`	Defensive Prompt Patch: A Robust and Generalizable Defense of Large Language Models against Jailbreak Attacks. ACL (Findings) Chen Xiong, Xiangyu Qi, Pin-Yu Chen, Tsung-Yi Ho
2025	J	`jnl`	Drone object detection incorporating multi-head mixed self-attention and dynamic regression mapping loss function. J. Real Time Image Process. Qinghua Su, Jianhong Mu, Sheng Xu, Kaizheng Wan, Xiangyu Qi, Zhichao Zhang, Juntao Li
2025	—	`conf`	Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability. NAACL (System Demonstrations) Haonan Li, Xudong Han, Zenan Zhai, Honglin Mu, Hao Wang, Zhenxuan Zhang, Yilin Geng, Shom Lin, Renxi Wang, Artem Shelmanov, Xiangyu Qi, Yuxia Wang, Donghai Hong, Youliang Yuan, Meng Chen, Haoqin Tu, Fajri Koto, Cong Zeng, Tatsuki Kuribayashi, Rishabh Bhardwaj, Bingchen Zhao, Yawen Duan, Yi Liu, Emad A. Alghamdi, Yaodong Yang, Yinpeng Dong, Soujanya Poria, Pengfei Liu, Zhengzhong Liu, Xuguang Ren, Eduard H. Hovy, Iryna Gurevych, Preslav Nakov, Monojit Choudhury, Timothy Baldwin
2025	A*	`conf`	On Evaluating the Durability of Safeguards for Open-Weight LLMs. ICLR Xiangyu Qi, Boyi Wei, Nicholas Carlini, Yangsibo Huang, Tinghao Xie, Luxi He, Matthew Jagielski, Milad Nasr, Prateek Mittal, Peter Henderson
2025	—	`conf`	OrbitText: A Hybrid Prediction System for Efficient and Effortless Text Entry in Virtual Reality. VR Workshops Zihao Li, Dongdong Weng, Xiaonuo Dongye, Jie Hao, Xiangyu Qi
2025	A*	`conf`	SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal. ICLR Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, Prateek Mittal
2025	A*	`conf`	Safety Alignment Should be Made More Than Just a Few Tokens Deep. ICLR Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson
2025	J	`jnl`	The Deployment of End-to-End Audio Language Models Should Take into Account the Principle of Least Privilege. CoRR Luxi He, Xiangyu Qi, Michel Liao, Inyoung Cheong, Prateek Mittal, Danqi Chen, Peter Henderson
2024	J	`jnl`	AI Risk Management Should Incorporate Both Safety and Security. CoRR Xiangyu Qi, Yangsibo Huang, Yi Zeng, Edoardo Debenedetti, Jonas Geiping, Luxi He, Kaixuan Huang, Udari Madhushani, Vikash Sehwag, Weijia Shi, Boyi Wei, Tinghao Xie, Danqi Chen, Pin-Yu Chen, Jeffrey Ding, Ruoxi Jia, Jiaqi Ma, Arvind Narayanan, Weijie J. Su, Mengdi Wang, Chaowei Xiao, Bo Li, Dawn Song, Peter Henderson, Prateek Mittal
2024	A*	`conf`	Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. ICML Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
2024	J	`jnl`	Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications. CoRR Boyi Wei, Kaixuan Huang, Yangsibo Huang, Tinghao Xie, Xiangyu Qi, Mengzhou Xia, Prateek Mittal, Mengdi Wang, Peter Henderson
2024	A*	`conf`	BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection. ICLR Tinghao Xie, Xiangyu Qi, Ping He, Yiming Li, Jiachen T. Wang, Prateek Mittal
2024	A*	`conf`	BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment. NeurIPS Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Junjie Hu, Sharon Li, Patrick McDaniel, Muhao Chen, Bo Li, Chaowei Xiao
2024	J	`jnl`	Computer-Vision-Based Sensing Technologies for Livestock Body Dimension Measurement: A Survey. Sensors Weihong Ma, Yi Sun, Xiangyu Qi, Xianglong Xue, Kaixuan Chang, Zhankang Xu, Mingyu Li, Rong Wang, Rui Meng, Qifeng Li
2024	J	`jnl`	Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks. CoRR Chen Xiong, Xiangyu Qi, Pin-Yu Chen, Tsung-Yi Ho
2024	A*	`conf`	Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! ICLR Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, Peter Henderson
2024	J	`jnl`	Libra-Leaderboard: Towards Responsible AI through a Balanced Leaderboard of Safety and Capability. CoRR Haonan Li, Xudong Han, Zenan Zhai, Honglin Mu, Hao Wang, Zhenxuan Zhang, Yilin Geng, Shom Lin, Renxi Wang, Artem Shelmanov, Xiangyu Qi, Yuxia Wang, Donghai Hong, Youliang Yuan, Meng Chen, Haoqin Tu, Fajri Koto, Tatsuki Kuribayashi, Cong Zeng, Rishabh Bhardwaj, Bingchen Zhao, Yawen Duan, Yi Liu, Emad A. Alghamdi, Yaodong Yang, Yinpeng Dong, Soujanya Poria, Pengfei Liu, Zhengzhong Liu, Xuguang Ren, Eduard H. Hovy, Iryna Gurevych, Preslav Nakov, Monojit Choudhury, Timothy Baldwin
2024	J	`jnl`	Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs. CoRR Ashwinee Panda, Berivan Isik, Xiangyu Qi, Sanmi Koyejo, Tsachy Weissman, Prateek Mittal
2024	J	`jnl`	Mitigating Fine-tuning Jailbreak Attack with Backdoor Enhanced Alignment. CoRR Jiongxiao Wang, Jiazhao Li, Yiquan Li, Xiangyu Qi, Junjie Hu, Yixuan Li, Patrick McDaniel, Muhao Chen, Bo Li, Chaowei Xiao
2024	J	`jnl`	On Evaluating the Durability of Safeguards for Open-Weight LLMs. CoRR Xiangyu Qi, Boyi Wei, Nicholas Carlini, Yangsibo Huang, Tinghao Xie, Luxi He, Matthew Jagielski, Milad Nasr, Prateek Mittal, Peter Henderson
2024	J	`jnl`	SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors. CoRR Tinghao Xie, Xiangyu Qi, Yi Zeng, Yangsibo Huang, Udari Madhushani Sehwag, Kaixuan Huang, Luxi He, Boyi Wei, Dacheng Li, Ying Sheng, Ruoxi Jia, Bo Li, Kai Li, Danqi Chen, Peter Henderson, Prateek Mittal
2024	J	`jnl`	Safety Alignment Should Be Made More Than Just a Few Tokens Deep. CoRR Xiangyu Qi, Ashwinee Panda, Kaifeng Lyu, Xiao Ma, Subhrajit Roy, Ahmad Beirami, Prateek Mittal, Peter Henderson
2024	A*	`conf`	Visual Adversarial Examples Jailbreak Aligned Large Language Models. AAAI Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Peter Henderson, Mengdi Wang, Prateek Mittal
2023	J	`jnl`	BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection. CoRR Tinghao Xie, Xiangyu Qi, Ping He, Yiming Li, Jiachen T. Wang, Prateek Mittal
2023	J	`jnl`	Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! CoRR Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, Peter Henderson
2023	A*	`conf`	Revisiting the Assumption of Latent Separability for Backdoor Defenses. ICLR Xiangyu Qi, Tinghao Xie, Yiming Li, Saeed Mahloujifar, Prateek Mittal
2023	A*	`conf`	Towards A Proactive ML Approach for Detecting Backdoor Poison Samples. USENIX Security Symposium Xiangyu Qi, Tinghao Xie, Jiachen T. Wang, Tong Wu, Saeed Mahloujifar, Prateek Mittal
2023	A*	`conf`	Uncovering Adversarial Risks of Test-Time Adaptation. ICML Tong Wu, Feiran Jia, Xiangyu Qi, Jiachen T. Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal
2023	J	`jnl`	Uncovering Adversarial Risks of Test-Time Adaptation. CoRR Tong Wu, Feiran Jia, Xiangyu Qi, Jiachen T. Wang, Vikash Sehwag, Saeed Mahloujifar, Prateek Mittal
2023	J	`jnl`	Visual Adversarial Examples Jailbreak Large Language Models. CoRR Xiangyu Qi, Kaixuan Huang, Ashwinee Panda, Mengdi Wang, Prateek Mittal
2022	J	`jnl`	Circumventing Backdoor Defenses That Are Based on Latent Separability. CoRR Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal
2022	J	`jnl`	Fight Poison with Poison: Detecting Backdoor Poison Samples via Decoupling Benign Correlations. CoRR Xiangyu Qi, Tinghao Xie, Saeed Mahloujifar, Prateek Mittal
2022	A*	`conf`	Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks. CVPR Xiangyu Qi, Tinghao Xie, Ruizhe Pan, Jifeng Zhu, Yong Yang, Kai Bu
2021	A*	`conf`	Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks. ICML Nezihe Merve Gürel, Xiangyu Qi, Luka Rimanic, Ce Zhang, Bo Li
2021	J	`jnl`	Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks. CoRR Nezihe Merve Gürel, Xiangyu Qi, Luka Rimanic, Ce Zhang, Bo Li
2021	J	`jnl`	Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting. CoRR Xiangyu Qi, Jifeng Zhu, Chulin Xie, Yong Yang
2021	J	`jnl`	Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks. CoRR Xiangyu Qi, Tinghao Xie, Ruizhe Pan, Jifeng Zhu, Yong Yang, Kai Bu
2020	J	`jnl`	SoK: Certified Robustness for Deep Neural Networks. CoRR Linyi Li, Xiangyu Qi, Tao Xie, Bo Li