Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models.

Kangjie Chen Shiqian Zhao Chong Wang 0013 Yiming Li 0004 Yihao Huang 0001 Wenjie Qu 0001 Siew-Kei Lam Yi Xie 0011 Kangjie Chen Jie Zhang 0073 Tianwei Zhang 0004 Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models. 2026 NDSS https://www.ndss-symposium.org/ndss-paper/towards-effective-prompt-stealing-attack-against-text-to-image-diffusion-models/ conf/ndss/2026 db/conf/ndss/ndss2026.html#ZhaoWLHQLXCZZ26

Renyang Liu 0001 Kangjie Chen Han Qiu 0001 Jie Zhang 0073 Kwok-Yan Lam Tianwei Zhang 0004 See-Kiong Ng SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models. 2026 January abs/2601.08623 CoRR https://doi.org/10.48550/arXiv.2601.08623 db/journals/corr/corr2601.html#abs-2601-08623 streams/journals/corr

Haoran Ou Kangjie Chen Gelei Deng Hangcheng Liu Jie Zhang 0073 Tianwei Zhang 0004 Kwok-Yan Lam DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems. 2026 February abs/2602.02569 CoRR https://doi.org/10.48550/arXiv.2602.02569 db/journals/corr/corr2602.html#abs-2602-02569 streams/journals/corr

Chaoda Zheng Sean Li Jinhao Deng Zhennan Wang Shijia Chen Liqiang Xiao Ziheng Chi Hongbin Lin Kangjie Chen Boyang Wang Yu Zhang Xianming Liu X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving. 2026 March abs/2603.19979 CoRR https://doi.org/10.48550/arXiv.2603.19979 db/journals/corr/corr2603.html#abs-2603-19979 streams/journals/corr

Dongbin Zhang Yunfei Liu 0001 Lijian Lin Ye Zhu 0003 Kangjie Chen Minghan Qin Yu Li 0003 Haoqian Wang HRAvatar: High-Quality and Relightable Gaussian Head Avatar. 26285-26296 2025 CVPR https://openaccess.thecvf.com/content/CVPR2025/html/Zhang_HRAvatar_High-Quality_and_Relightable_Gaussian_Head_Avatar_CVPR_2025_paper.html https://doi.org/10.1109/CVPR52734.2025.02448 conf/cvpr/2025 db/conf/cvpr/cvpr2025.html#ZhangLLZCQLW25 Kangjie Chen Muyang Li Guanlin Li Shudong Zhang Shangwei Guo Tianwei Zhang 0004 TRUST-VLM: Thorough Red-Teaming for Uncovering Safety Threats in Vision-Language Models. 2025 ICML https://proceedings.mlr.press/v267/chen25au.html https://openreview.net/forum?id=dc9vh0NlBR conf/icml/2025 db/conf/icml/icml2025.html#ChenLLZG025 Kangjie Chen BingQuan Dai Minghan Qin Dongbin Zhang Peihao Li 0003 Yingshuang Zou Haoqian Wang SLGaussian: Fast Language Gaussian Splatting in Sparse Views. 3047-3056 2025 ACM Multimedia https://doi.org/10.1145/3746027.3754964 conf/mm/2025 db/conf/mm/mm2025.html#ChenDQZ0ZW25 Yuyang Zhang Kangjie Chen Xudong Jiang Jiahui Wen Yihui Jin Ziyou Liang Yihao Huang 0001 Run Wang 0001 Lina Wang 0001 USD: NSFW Content Detection for Text-to-Image Models via Scene Graph. 879-895 2025 USENIX Security Symposium https://www.usenix.org/conference/usenixsecurity25/presentation/zhang-yuyang conf/uss/2025 db/conf/uss/uss2025.html#ZhangCJWJL00025

Guanlin Li Kangjie Chen Shangwei Guo Jie Zhang 0073 Han Qiu 0001 Chao Zhang 0008 Guoyin Wang 0002 Tianwei Zhang 0004 Jiwei Li 0001 Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning. 2025 February abs/2502.01116 CoRR https://doi.org/10.48550/arXiv.2502.01116 db/journals/corr/corr2502.html#abs-2502-01116 streams/journals/corr

Dongbin Zhang Yunfei Liu 0001 Lijian Lin Ye Zhu 0003 Kangjie Chen Minghan Qin Yu Li 0003 Haoqian Wang HRAvatar: High-Quality and Relightable Gaussian Head Avatar. 2025 March abs/2503.08224 CoRR https://doi.org/10.48550/arXiv.2503.08224 db/journals/corr/corr2503.html#abs-2503-08224 streams/journals/corr

Zihan Wang Hongwei Li 0001 Rui Zhang 0090 Wenbo Jiang 0001 Kangjie Chen Tianwei Zhang 0004 Qingchuan Zhao Guowen Xu BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models. 2025 May abs/2505.03501 CoRR https://doi.org/10.48550/arXiv.2505.03501 db/journals/corr/corr2505.html#abs-2505-03501 streams/journals/corr

Wenjie Li 0008 Siying Gu Yiming Li 0004 Kangjie Chen Zhili Chen Tianwei Zhang 0004 Shu-Tao Xia Dacheng Tao Coward: Toward Practical Proactive Federated Backdoor Defense via Collision-based Watermark. 2025 August abs/2508.02115 CoRR https://doi.org/10.48550/arXiv.2508.02115 db/journals/corr/corr2508.html#abs-2508-02115 streams/journals/corr

Yanzhou Li Shangqing Liu Kangjie Chen Tianwei Zhang Yang Liu Impact-driven Context Filtering For Cross-file Code Completion. 2025 August abs/2508.05970 CoRR https://doi.org/10.48550/arXiv.2508.05970 db/journals/corr/corr2508.html#abs-2508-05970 streams/journals/corr

Shiqian Zhao Chong Wang 0013 Yiming Li 0004 Yihao Huang 0001 Wenjie Qu 0001 Siew-Kei Lam Yi Xie 0011 Kangjie Chen Jie Zhang 0073 Tianwei Zhang 0004 Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models. 2025 August abs/2508.06837 CoRR https://doi.org/10.48550/arXiv.2508.06837 db/journals/corr/corr2508.html#abs-2508-06837 streams/journals/corr

Kangjie Chen Yingji Zhong Zhihao Li Jiaqi Lin Youyu Chen Minghan Qin Haoqian Wang Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting. 2025 August abs/2508.12720 CoRR https://doi.org/10.48550/arXiv.2508.12720 db/journals/corr/corr2508.html#abs-2508-12720 streams/journals/corr

Anindya Sundar Das 0002 Kangjie Chen Monowar Bhuyan Unmasking Backdoors: An Explainable Defense via Gradient-Attention Anomaly Scoring for Pre-trained Language Models. 2025 October abs/2510.04347 CoRR https://doi.org/10.48550/arXiv.2510.04347 db/journals/corr/corr2510.html#abs-2510-04347 streams/journals/corr

Haoran Ou Kangjie Chen Xingshuo Han Gelei Deng Jie Zhang 0073 Han Qiu 0001 Tianwei Zhang 0004 CREST-Search: Comprehensive Red-teaming for Evaluating Safety Threats in Large Language Models Powered by Web Search. 2025 October abs/2510.09689 CoRR https://doi.org/10.48550/arXiv.2510.09689 db/journals/corr/corr2510.html#abs-2510-09689 streams/journals/corr

Jiaming He Guanyu Hou Hongwei Li 0001 Zhicong Huang Kangjie Chen Yi Yu Wenbo Jiang 0001 Guowen Xu Tianwei Zhang 0004 TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models. 2025 November abs/2511.21145 CoRR https://doi.org/10.48550/arXiv.2511.21145 db/journals/corr/corr2511.html#abs-2511-21145 streams/journals/corr

Renyang Liu 0001 Wei Zhou 0011 Tianwei Zhang 0004 Kangjie Chen Jun Zhao 0007 Kwok-Yan Lam Boosting Black-Box Attack to Deep Neural Networks With Conditional Diffusion Models. 5207-5219 2024 19 IEEE Trans. Inf. Forensics Secur. https://doi.org/10.1109/TIFS.2024.3390609 db/journals/tifs/tifs19.html#LiuZZCZL24

Xiaoxuan Lou Kangjie Chen Guowen Xu Han Qiu 0001 Shangwei Guo Tianwei Zhang 0004 Protecting Confidential Virtual Machines from Hardware Performance Counter Side Channels. 195-208 2024 DSN https://doi.org/10.1109/DSN58291.2024.00031 https://dsn2024uq.github.io/Proceedings/pdfs/DSN2024-6rvE3SSpzFYmysif75Dkid/410500a195/410500a195.pdf conf/dsn/2024 db/conf/dsn/dsn2024.html#LouCXQGZ24 streams/conf/dsn Yanzhou Li Tianlin Li Kangjie Chen Jian Zhang 0087 Shangqing Liu Wenhan Wang Tianwei Zhang 0004 Yang Liu 0003 BadEdit: Backdooring Large Language Models by Model Editing. 2024 ICLR https://openreview.net/forum?id=duZANm2ABX conf/iclr/2024 db/conf/iclr/iclr2024.html#LiLCZLW0024 Hao Wang 0227 Shangwei Guo Jialing He Kangjie Chen Shudong Zhang Tianwei Zhang 0004 Tao Xiang 0001 EvilEdit: Backdooring Text-to-Image Diffusion Models in One Second. 3657-3665 2024 ACM Multimedia https://doi.org/10.1145/3664647.3680689 https://www.wikidata.org/entity/Q131015880 conf/mm/2024 db/conf/mm/mm2024.html#0003GHCZ0024 Guanlin Li Kangjie Chen Shudong Zhang Jie Zhang 0073 Tianwei Zhang 0004 ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/a5c7206fd66e8314bb21a04492359353-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#LiCZZZ24

Peiheng Zhou Ming Hu 0003 Xiaofei Xie Yihao Huang 0001 Kangjie Chen Mingsong Chen 0001 MIP: CLIP-based Image Reconstruction from PEFT Gradients. 2024 abs/2403.07901 CoRR https://doi.org/10.48550/arXiv.2403.07901 db/journals/corr/corr2403.html#abs-2403-07901

Yanzhou Li Tianlin Li Kangjie Chen Jian Zhang 0087 Shangqing Liu Wenhan Wang Tianwei Zhang 0004 Yang Liu 0003 BadEdit: Backdooring large language models by model editing. 2024 abs/2403.13355 CoRR https://doi.org/10.48550/arXiv.2403.13355 db/journals/corr/corr2403.html#abs-2403-13355

Guanlin Li Kangjie Chen Shudong Zhang Jie Zhang Tianwei Zhang 0004 ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users. 2024 abs/2405.19360 CoRR https://doi.org/10.48550/arXiv.2405.19360 db/journals/corr/corr2405.html#abs-2405-19360

Kangjie Chen BingQuan Dai Minghan Qin Dongbin Zhang Peihao Li 0003 Yingshuang Zou Haoqian Wang SLGaussian: Fast Language Gaussian Splatting in Sparse Views. 2024 abs/2412.08331 CoRR https://doi.org/10.48550/arXiv.2412.08331 db/journals/corr/corr2412.html#abs-2412-08331 streams/journals/corr

Yuyang Zhang Kangjie Chen Xudong Jiang Yuxiang Sun Run Wang 0001 Lina Wang 0001 Towards Action Hijacking of Large Language Model-based Agent. 2024 abs/2412.10807 CoRR https://doi.org/10.48550/arXiv.2412.10807 db/journals/corr/corr2412.html#abs-2412-10807 streams/journals/corr

Xingshuo Han Yuan Zhou 0005 Kangjie Chen Han Qiu 0001 Meikang Qiu Yang Liu 0003 Tianwei Zhang 0004 ADS-Lead: Lifelong Anomaly Detection in Autonomous Driving Systems. 1039-1051 2023 January 24 IEEE Trans. Intell. Transp. Syst. 1 https://doi.org/10.1109/TITS.2021.3122906 db/journals/tits/tits24.html#HanZCQQLZ23

Yanzhou Li Shangqing Liu Kangjie Chen Xiaofei Xie Tianwei Zhang 0004 Yang Liu 0003 Multi-target Backdoor Attacks for Code Pre-trained Models. 7236-7254 2023 ACL (1) https://doi.org/10.18653/v1/2023.acl-long.399 https://aclanthology.org/2023.acl-long.399 https://www.wikidata.org/entity/Q131458456 conf/acl/2023-1 db/conf/acl/acl2023-1.html#LiLCX0023 Kangjie Chen Xiaoxuan Lou Guowen Xu Jiwei Li 0001 Tianwei Zhang 0004 Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only. 2023 ICLR https://openreview.net/forum?id=rFQfjDC9Mt conf/iclr/2023 db/conf/iclr/iclr2023.html#ChenLX0023 Hanxiao Chen 0001 Meng Hao 0001 Hongwei Li 0001 Kangjie Chen Guowen Xu Tianwei Zhang 0004 Xilin Zhang GuardHFL: Privacy Guardian for Heterogeneous Federated Learning. 4566-4584 2023 ICML https://proceedings.mlr.press/v202/chen23j.html conf/icml/2023 db/conf/icml/icml2023.html#ChenHLCX0Z23

Shiqian Zhao Kangjie Chen Meng Hao 0001 Jian Zhang 0001 Guowen Xu Hongwei Li 0001 Tianwei Zhang 0004 Extracting Cloud-based Model with Prior Knowledge. 2023 abs/2306.04192 CoRR https://doi.org/10.48550/arXiv.2306.04192 db/journals/corr/corr2306.html#abs-2306-04192

Yanzhou Li Shangqing Liu Kangjie Chen Xiaofei Xie Tianwei Zhang 0004 Yang Liu 0003 Multi-target Backdoor Attacks for Code Pre-trained Models. 2023 abs/2306.08350 CoRR https://doi.org/10.48550/arXiv.2306.08350 db/journals/corr/corr2306.html#abs-2306-08350

Guanlin Li Kangjie Chen Yuan Xu Han Qiu 0001 Tianwei Zhang 0004 Omnipotent Adversarial Training for Unknown Label-noisy and Imbalanced Datasets. 2023 abs/2307.08596 CoRR https://doi.org/10.48550/arXiv.2307.08596 db/journals/corr/corr2307.html#abs-2307-08596

Renyang Liu 0001 Wei Zhou 0011 Tianwei Zhang 0004 Kangjie Chen Jun Zhao 0007 Kwok-Yan Lam Boosting Black-box Attack to Deep Neural Networks with Conditional Diffusion Models. 2023 abs/2310.07492 CoRR https://doi.org/10.48550/arXiv.2310.07492 db/journals/corr/corr2310.html#abs-2310-07492

Kangjie Chen Yuxian Meng Xiaofei Sun 0001 Shangwei Guo Tianwei Zhang 0004 Jiwei Li 0001 Chun Fan 0001 BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models. 2022 ICLR https://openreview.net/forum?id=Mng8CQ9eBW conf/iclr/2022 db/conf/iclr/iclr2022.html#ChenMSG0LF22

Xiaoxuan Lou Guowen Xu Kangjie Chen Guanlin Li Jiwei Li 0001 Tianwei Zhang 0004 ShiftNAS: Towards Automatic Generation of Advanced Mulitplication-Less Neural Networks. 2022 abs/2204.05113 CoRR https://doi.org/10.48550/arXiv.2204.05113 db/journals/corr/corr2204.html#abs-2204-05113

Yan Zheng 0002 Ziming Yan Kangjie Chen Jianwen Sun Yan Xu 0005 Yang Liu 0003 Vulnerability Assessment of Deep Reinforcement Learning Models for Power System Topology Optimization. 3613-3623 2021 12 IEEE Trans. Smart Grid 4 https://doi.org/10.1109/TSG.2021.3062700 db/journals/tsg/tsg12.html#ZhengYCSXL21

Kangjie Chen Shangwei Guo Tianwei Zhang 0004 Xiaofei Xie Yang Liu 0003 Stealing Deep Reinforcement Learning Models for Fun and Profit. 307-319 2021 AsiaCCS https://doi.org/10.1145/3433210.3453090 conf/asiaccs/2021 db/conf/asiaccs/asiaccs2021.html#ChenGZXL21 Kangjie Chen Shangwei Guo Tianwei Zhang 0004 Shuxin Li 0001 Yang Liu 0003 Temporal Watermarks for Deep Reinforcement Learning Models. 314-322 2021 AAMAS https://www.ifaamas.org/Proceedings/aamas2021/pdfs/p314.pdf https://dl.acm.org/doi/10.5555/3463952.3463994 conf/atal/2021 db/conf/atal/aamas2021.html#ChenGZLL21 Xingshuo Han Kangjie Chen Yuan Zhou 0005 Meikang Qiu Chun Fan 0001 Yang Liu 0003 Tianwei Zhang 0004 A Unified Anomaly Detection Methodology for Lane-Following of Autonomous Driving Systems. 836-844 2021 ISPA/BDCloud/SocialCom/SustainCom https://doi.org/10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00119 conf/ispa/2021 db/conf/ispa/ispa2021.html#HanCZQFLZ21

Kangjie Chen Yuxian Meng Xiaofei Sun 0001 Shangwei Guo Tianwei Zhang 0004 Jiwei Li 0001 Chun Fan 0001 BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models. 2021 abs/2110.02467 CoRR https://arxiv.org/abs/2110.02467 db/journals/corr/corr2110.html#abs-2110-02467

Jianwen Sun Tianwei Zhang 0004 Xiaofei Xie Lei Ma 0003 Yan Zheng 0002 Kangjie Chen Yang Liu 0003 Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning. 5883-5891 2020 AAAI https://doi.org/10.1609/aaai.v34i04.6047 conf/aaai/2020 db/conf/aaai/aaai2020.html#SunZX0ZCL20

Jianwen Sun Tianwei Zhang 0004 Xiaofei Xie Lei Ma 0003 Yan Zheng 0002 Kangjie Chen Yang Liu 0003 Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learning. 2020 abs/2005.07099 CoRR https://arxiv.org/abs/2005.07099 db/journals/corr/corr2005.html#abs-2005-07099

Kangjie Chen Tianwei Zhang 0004 Xiaofei Xie Yang Liu 0003 Stealing Deep Reinforcement Learning Models for Fun and Profit. 2020 abs/2006.05032 CoRR https://arxiv.org/abs/2006.05032 db/journals/corr/corr2006.html#abs-2006-05032

Shuxin Li 0001 Xiaohong Li 0001 Jianye Hao Bo An 0001 Zhiyong Feng 0002 Kangjie Chen Chengwei Zhang 0001 Defending Against Man-In-The-Middle Attack in Repeated Games. 3742-3748 2017 IJCAI https://doi.org/10.24963/ijcai.2017/523 conf/ijcai/2017 db/conf/ijcai/ijcai2017.html#LiLHAFCZ17 Bo An 0001 Monowar Bhuyan Hanxiao Chen 0001 Mingsong Chen 0001 Shijia Chen Youyu Chen Zhili Chen Ziheng Chi BingQuan Dai Anindya Sundar Das 0002 Gelei Deng Jinhao Deng Chun Fan 0001 Zhiyong Feng 0002 Siying Gu Shangwei Guo Xingshuo Han Jianye Hao Meng Hao 0001 Jialing He Jiaming He Guanyu Hou Ming Hu 0003 Yihao Huang 0001 Zhicong Huang Wenbo Jiang 0001 Xudong Jiang Yihui Jin Kwok-Yan Lam Siew-Kei Lam Guanlin Li Hongwei Li 0001 Jiwei Li 0001 Muyang Li Peihao Li 0003 Sean Li Shuxin Li 0001 Tianlin Li Wenjie Li 0008 Xiaohong Li 0001 Yanzhou Li Yiming Li 0004 Yu Li 0003 Zhihao Li Ziyou Liang Hongbin Lin Jiaqi Lin Lijian Lin Hangcheng Liu Renyang Liu 0001 Shangqing Liu Xianming Liu Yang Liu Yang Liu 0003 Yunfei Liu 0001 Xiaoxuan Lou Lei Ma 0003 Yuxian Meng See-Kiong Ng Haoran Ou Minghan Qin Han Qiu 0001 Meikang Qiu Wenjie Qu 0001 Jianwen Sun Xiaofei Sun 0001 Yuxiang Sun Dacheng Tao Boyang Wang Chong Wang 0013 Guoyin Wang 0002 Hao Wang 0227 Haoqian Wang Lina Wang 0001 Run Wang 0001 Wenhan Wang Zhennan Wang Zihan Wang Jiahui Wen Shutao XiaShu-Tao Xia Tao Xiang 0001 Liqiang Xiao Xiaofei Xie Yi Xie 0011 Guowen Xu Yan Xu 0005 Yuan Xu Ziming Yan Yi Yu Chao Zhang 0008 Chengwei Zhang 0001 Dongbin Zhang Jian Zhang 0001 Jian Zhang 0087 Jie Zhang Jie Zhang 0073 Rui Zhang 0090 Shudong Zhang Tianwei Zhang Tianwei Zhang 0004 Xilin Zhang Yu Zhang Yuyang Zhang Jun Zhao 0007 Qingchuan Zhao Shiqian Zhao Chaoda Zheng Yan Zheng 0002 Yingji Zhong Peiheng Zhou Wei Zhou 0011 Yuan Zhou 0005 Ye Zhu 0003 Yingshuang Zou