About me

I am currently a second-year master’s student in the School of Cyber Science and Engineering at Huazhong University of Science and Technology, Wuhan, China, supervised by Professor Shengshan Hu from TAI group. Prior to that, I obtained a Bachelor of Engineering degree from Huazhong University of Science and Technology in 2022.

My current research interest focuses on trustworthy AI, embodied AI, AIGC, and etc. I am always open for any research communication and cooperation, please don’t hesitate to contact me if you are interested. Email address: wxl99 at hust.edu.cn

Publications

DarkSAM: Fooling Segment Anything Model to Segment Nothing
Ziqi Zhou, Yufei Song, Minghui Li, Shengshan Hu, Xianlong Wang, Leo Yu Zhang, Dezhong Yao, Hai Jin
In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024) (Acceptance rate=25.8%)

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
Xianlong Wang, Minghui Li, Wei Liu, Hangtao Zhang, Shengshan Hu, Yechao Zhang, Ziqi Zhou, Hai Jin
In Proceedings of the 38th Annual Conference on Neural Information Processing Systems (NeurIPS 2024) (Acceptance rate=25.8%)

ECLIPSE: Expunging Clean-Label Indiscriminate Poisons via Sparse Diffusion Purification
Xianlong Wang, Shengshan Hu, Yechao Zhang, Ziqi Zhou, Leo Yu Zhang, Peng Xu, Wei Wan, Hai Jin
In Proceedings of the 29th European Symposium on Research in Computer Security (ESORICS 2024) (Acceptance rate: 86/535=16%)

PointAPA: Towards Availability Poisoning Attacks in 3D Point Clouds
Xianlong Wang, Minghui Li, Peng Xu, Wei Liu, Leo Yu Zhang, Shengshan Hu, Yanjun Zhang
In Proceedings of the 29th European Symposium on Research in Computer Security (ESORICS 2024) (Acceptance rate: 86/535=16%)

Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness in the Physical World
Hangtao Zhang, Shengshan Hu, Yichen Wang, Leo Yu Zhang, Ziqi Zhou, Xianlong Wang, Yanjun Zhang, Chao Chen
In Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024) (Acceptance rate=14%)

PointCRT: Detecting Backdoor in 3D Point Cloud via Corruption Robustness
Shengshan Hu, Wei Liu, Minghui Li, Yechao Zhang, Xiaogeng Liu, Xianlong Wang, Leo Yu Zhang, Junhui Hou
In Proceedings of the 31st ACM International Conference on Multimedia (MM 2023) (Oral) (Acceptance rate=29.3%)

Pre-prints

BadRobot: Jailbreaking LLM-based Embodied AI in the Physical World
Hangtao Zhang, Chenyu Zhu, Xianlong Wang, Ziqi Zhou, Shengshan Hu, Leo Yu Zhang
arXiv preprint arXiv:2407.20242 (arXiv 2024)

Corrupting Convolution-based Unlearnable Datasets with Pixel-based Image Transformations
Xianlong Wang, Shengshan Hu, Minghui Li, Zhifei Yu, Ziqi Zhou, Leo Yu Zhang
arXiv preprint arXiv:2311.18403 (arXiv 2023)

Services

Reviewer for MM’24, NeurIPS’24 Workshop, ICPR’24, ICASSP’25, ICLR’25

Competitions

Face Recognition Security Competition in Artificial Intelligence Security Competition (2022) (Excellence Award)
Haoyu Wang, Yechao Zhang, Xiaogeng Liu, Xianlong Wang, Ziqi Zhou

National College Student Information Security Competition (2021) (Third Prize)
Xianlong Wang, Ao Yang, Yiman Hu, Junyu Shi

Mathematical Contest In Modeling (2021) (Honorable Mention)
Xianlong Wang, Yiman Hu

Awards

National Scholarship (2024) (Top 0.2%)
Scholarship for Postgraduates, Huazhong University of Sci. and Tech. (2023) (Second Prize)
Excellent Postgraduate Cadre, Huazhong University of Sci. and Tech. (2023)
Scholarship for Postgraduates, Huazhong University of Sci. and Tech. (2022) (First Prize)
Outstanding Graduate, Huazhong University of Sci. and Tech. (2022)
Scholarship for Academic Excellence, Huazhong University of Sci. and Tech. (2021)
Outstanding Student Cadres, Huazhong University of Sci. and Tech. (2021)
Scholarship for Self-improvement, Huazhong University of Sci. and Tech. (2020)
Scholarship for Academic Progress, Huazhong University of Sci. and Tech. (2019)