↑

Selected Publications


A complete list can be found in [Google Scholar]

[AAAI'26]   MacPrompt: Maraconic-guided Jailbreak against Text-to-Image Models [CCF-A]

Xi Ye, Yiwen Liu, Lina Wang, Run Wang*, Geying Yang, Yufei Hou, Jiayi Yu
AAAI Conference on Artificial Intelligence (AAAI), 2026

[AAAI'26]   PCFormer: Accelerating Privacy-preserving Transformer Inference by Partition and Combination [CCF-A]

Bo Zeng, Zhi Pang, Yuyang Zhang, Kai Zhao, Tian Wu, Geying Yang, Lina Wang, Run Wang*
AAAI Conference on Artificial Intelligence (AAAI), 2026

[IEEE S&P'26]   DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling [CCF-A]

Boheng Li, Junjie Wang, Yiming Li, Zhiyang Hu, Leyi Qi, Jianshuo Dong, Run Wang, Han Qiu, Zhan Qin, Tianwei Zhang
The IEEE Symposium on Security and Privacy (IEEE S&P), 2026

[NeurIPS'25]   Analogy-based Multi-Turn Jailbreak against Large Language Models [CCF-A]

Mengjie Wu, Yihao Huang, Zhenjun Lin, Kangjie Chen, Yuyang Zhang, Yuhan Huang, Run Wang*, Lina Wang
Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

[NeurIPS'25]   Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning [CCF-A]

Boheng Li, Renjie Gu, Junjie Wang, Leyi Qi, Yiming Li, Run Wang, Zhan Qin, Tianwei Zhang
Annual Conference on Neural Information Processing Systems (NeurIPS), 2025

[ICCV'25]   Automated Red Teaming for Text-to-Image Models through Feedback-Guided Prompt Iteration with Vision-Language Models [CCF-A]

Wei Xu, Kangjie Chen, Jiawei Qiu, Yuyang Zhang, Run Wang*, Jin Mao, Tianwei Zhang, Lina Wang
International Conference on Computer Vision (ICCV’25) , Honolulu, Hawaii

[USENIX Sec.'25]   USD: NSFW Content Detection for Text-to-Image Models via Scene Graph [CCF-A]

Yuyang Zhang, Kangjie Chen, Xudong Jiang, Jiahui Wen, Yihui Jin, Ziyou Liang, Yihao Huang, Run Wang*, Lina Wang
The USENIX Security Symposium (USENIX Security), 2025

[IJCAI'25]   HIPP: Protecting Image Privacy via High-Quality Reversible Protected Version [CCF-A]

Xi Ye, Lina Wang, Run Wang*, Jiatong Liu, Geying Yang
Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) , 2025

[AAAI'25]   Perception-guided Jailbreak against Text-to-Image Models [CCF-A]

Yihao Huang, Le Liang, Tianlin Li, Xiaojun Jia, Run Wang, Weikai Miao, Geguang Pu, Yang Liu
AAAI Conference on Artificial Intelligence (AAAI), 2025

[AAAI'25]   Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection [CCF-A]

Ziyou Liang, Weifeng Liu, Run Wang*, Mengjie Wu, Boheng Li, Yuyang Zhang, Lina Wang, Xinyi Yang
AAAI Conference on Artificial Intelligence (AAAI), 2025

[IEEE S&P'25]   Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models [CCF-A]

Boheng Li, Yanhao Wei, Yankai Fu, Zhenting Wang, Yiming Li, Jie Zhang, Run Wang, Tianwei Zhang
The IEEE Symposium on Security and Privacy (IEEE S&P), 2025

[ICML'24]   Purifying Quantization-conditioned Backdoors via Layer-wise Activation with Distribution Correction Approximation [CCF-A]

Boheng Li, Yishuo Cai, Jisong Cai, Yiming Li, Han Qiu, Run Wang, Tianwei Zhang
The International Conference on Machine Learning (ICML), 2024

[NeurIPS'24]   Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes [CCF-A]

Weifeng Liu, Tianyi She, Jiawei Liu, Boheng Li, Dongyu Yao, Ziyou Liang, Run Wang*
Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

[TIFS'24]   Hard Adversarial Example Mining for Improving Robust Fairness [CCF-A]

Chenhao Lin, Xiang Ji, Yulong Yang, Qian Li, Zhengyu Zhao, Zhe Peng, Run Wang, Liming Fang, Chao Shen
IEEE Transactions on Information Forensics and Security (IEEE TIFS), 2024

[AAAI'24]   TraceEvader: Making DeepFakes More Untraceable via Evading the Forgery Model Attribution [CCF-A]

Mengjie Wu, Jingui Ma, Run Wang*, Sidan Zhang, Boheng Li, Chenhao Lin, Liming Fang, Lina Wang
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI’24) , Vancouver, Canada

[ACM MM'23]    Free Fine-tuning: A Plug-and-Play Watermarking Scheme for Deep Neural Networks [CCF-A]

Run Wang, Jixing Ren, Boheng Li, Tianyi She, Wenhui Zhang, Liming Fang, Jing Chen, Lina Wang
1th ACM International Conference on Multimedia (ACM MM’23) , Ottawa, Canada

[ICCV'23]   What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Networks[CCF-A]

Ziheng Huang#, Boheng Li#, Yan Cai, Run Wang*, Shangwei Guo, Liming Fang, Jing Chen, Lina Wang
International Conference on Computer Vision (ICCV’23) , Paris, France

[ACM MM'22]   Rethinking the Vulnerability of DNN Watermarking: Are Watermarks Robust against Naturalness-aware Perturbations? [CCF-A]

Run Wang, Haoxuan Li, Lingzhou Mu, Jixing Ren, Shangwei Guo, Li Liu, Liming Fang, Jing Chen, Lina Wang
30th ACM International Conference on Multimedia (ACM MM’22) , Lisbon, Portugal

[IJCAI'22]   Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations[CCF-A]

Run Wang, Ziheng Huang, Zhikai Chen, Li Liu, Jing Chen, Lina Wang.
Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI’22) , Vienna, Austria

[IJCAI'22]   MetaFinger: Fingerprinting the Deep Neural Networks with Meta-training[CCF-A]

Kang Yang, Run Wang*, Lina Wang.
Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI’22), Vienna, Austria

[IJCV'22]    Countering Malicious DeepFakes: Survey, Battleground, and Horizon[CCF-A]

Felix Juefei-Xu, Run Wang*, Yihao Huang, Qing Guo, Lei Ma, Yang Liu.
International Journal of Computer Vision (IJCV) 2022

[TKDE'21]   Towards a Robust Deep Neural Network against Adversarial Texts: A Survey[CCF-A]

Wenqi Wang, Run Wang*, Lina Wang, Zhibo Wang, Aoshuang Ye.
IEEE Transactions on Knowledge and Data Engineering (TKDE) 2021

[ACM MM'21]   FakeTagger: Robust Safeguards against DeepFake Dissemination via Provenance Tracking[CCF-A]

Run Wang, Felix Juefei-Xu, Meng Luo, Yang Liu, Lina Wang.
29th ACM International Conference on Multimedia (ACM MM’21), Chengdu, China.
Media coverage: Unit.AI, 新智元.

[ACM MM'20]    DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices[CCF-A]

Run Wang, Felix Juefei-Xu, Yihao Huang, Qing Guo, Xiaofei Xie, Lei Ma, Yang Liu.
28th ACM International Conference on Multimedia (ACM MM’20), Seattle, USA. (Oral Presentation)

[ACM MM'20]   Amora: Black-box Adversarial Morphing Attack[CCF-A]

Run Wang, Felix Juefei-Xu, Qing Guo, Yihao Huang, Xiaofei Xie, Lei Ma, Yang Liu.
28th ACM International Conference on Multimedia (ACM MM’20), Seattle, USA. (Oral Presentation)

[ACM MM'20]   FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction[CCF-A]

Yihao Huang, Felix Juefei-Xu,Run Wang*, Qing Guo, Lei Ma, Xiaofei Xie, Jianwen Li, Weikai Miao, Yang Liu, Geguang Pu.
28th ACM International Conference on Multimedia (ACM MM’20), Seattle, USA. (Oral Presentation)

[ACM MM'20]   MGAttack: Toward More Query-efficient Black-box Attack by Microbial Genetic Algorithm[CCF-A]

Lina Wang, Kang Yang, Wenqi Wang, Run Wang*, Aoshuang Ye.
28th ACM International Conference on Multimedia (ACM MM’20), Seattle, USA.

[IJCAI'20]    FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces[CCF-A]

Run Wang, Felix Juefei-Xu, Lei Ma, Xiaofei Xie, Yihao Huang, Jian Wang and Yang Liu.
Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI’20), Yokohama, Japan.
Media coverage: Synced Review.

[IEEE TMC'20]    SmartPI: Understanding Permission Implications of Android Apps from User Reviews[CCF-A]

Run Wang, Zhibo Wang, Benxiao Tang, Lei Zhao, Lina Wang.
IEEE Transactions on Mobile Computing(TMC), 19(12), 2020: 2933-2945
See More See Less
Copyright © S2PE Lab.
Designed and Developed by Zhihao Peng.