I am currently a second-year Ph.D. student advised by Prof. Shengshan Hu, Leo Yu Zhang and Dezhong Yao in School of Computer Science and Technology at Huazhong University of Science and Technology (HUST) and affiliated with Creativity, Greatness, Communication, and Love (CGCL) Lab, Trustworthy Artificial Intelligence (T-AI) Group.

I am an enthusiastic researcher with a passion for exploring new ideas and pushing the boundaries of knowledge. In addition to my academic pursuits, I am also an avid debater and enjoy participating in debate competitions. I find great satisfaction in the process of thinking critically and exchanging ideas with others, and I believe that this skillset has been invaluable in my pursuit of academic excellence. I am committed to pursuing research that not only advances our understanding of the world around us, but also has the potential to positively impact society at large.

Research Interests

As a researcher in the field of artificial intelligence (AI), my primary interest lies in the area of AI security. Specifically, I am interested in the study of Adversarial Examples and Backdoor Attacks, with a recent focus on the security of pre-trained large models (PLMs) and the vulnerability of Image Segmentation and Object Detection to adversarial attacks. My research aims to develop robust and secure AI systems that can withstand various types of attacks and ensure the safety and reliability of AI applications. Through my work, I hope to contribute to the advancement of AI security and establish a more secure and trustworthy AI ecosystem. If you’d like to discuss potential research opportunities or simply connect, please don’t hesitate to reach out to me at zhouziqi@hust.edu.cn.

Publication

• Hangtao Zhang, Chengyu Zhu, Xianlong Wang, Ziqi Zhou, Shengshan Hu, Leo Yu Zhang. BadRobot: Jailbreaking LLM-based Embodied AI in the Physical World. arXiv. 2024. [Code][pdf]
• Minghui Li, Jiangxiong Wang, Hao Zhang, Ziqi Zhou*, Shengshan Hu, Xiaobing Pei. Transferable Adversarial Facial Images for Privacy Protection. In Proceedings of ACM MM. 2024. [Code][pdf]
• Xianlong Wang, Shengshan Hu, Yechao Zhang, Ziqi Zhou, Leo Yu Zhang, Peng Xu, Wei Wan, Hai Jin. ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification. In Proceedings of ESORICS. 2024. [Code][pdf]
• Hangtao Zhang, Shengshan Hu, Yichen Wang, Leo Yu Zhang, Ziqi Zhou, Xianlong Wang, Yanjun Zhang, Chao Chen. Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness. In Proceedings of IJCAI. 2024. [Code][pdf]
• Ziqi Zhou, Minghui Li, Wei Liu, Shengshan Hu, Yechao Zhang, Wei Wan, Lulu Xue, Leo Yu Zhang, Dezhong Yao, Hai Jin. Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples. In Proceedings of IEEE S&P. 2024. [Code][pdf]
• Xianlong Wang, Shengshan Hu, Minghui Li, Zhifei Yu, Ziqi Zhou, Leo Yu Zhang, Hai Jin. Corrupting Unbounded Unlearnable Datasets with Pixel-based Image Transformations. arXiv. 2023. [Code][pdf]
• Wei Wan, Shengshan Hu, Jianrong Lu, Minghui Li, Ziqi Zhou, Hai Jin. Generalisation Robustness Enhancement for Federal Learning in Highly Data Heterogeneous Scenarios. In SCIENTIA SINICA Informationis. 2023. [Code][pdf]
• Ziqi Zhou, Shengshan Hu, Minghui Li, Hangtao Zhang, Yechao Zhang, Hai Jin. AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning. In Proceedings of ACM MM. 2023. [Code][pdf]
• Ziqi Zhou, Shengshan Hu, Ruizhi Zhao, Qian Wang, Leo Yu Zhang, Junhui Hou, Hai Jin. Downstream-agnostic Adversarial Examples. In Proceedings of IEEE ICCV. 2023. [Code][pdf]
• Shengshan Hu, Ziqi Zhou, Yechao Zhang, Leo Yu Zhang, Yifeng Zheng, Yuanyuan He, Hai Jin. BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label. In Proceedings of ACM MM. 2022. [Code][pdf]

* indicates the corresponding author

Professional Services

Serve as a reviewer for the following international journals & conferences:

• IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI, CCF A)
• IEEE Transactions on Information Systems (TOIS, CCF A)
• The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS, CCF A)
• International Conference on Learning Representations 2025 (ICLR)
• ACM Mutimeda 2023/2024 (ACM MM, CCF A)
• Computer Vision and Image Understanding (CVIU, CCF B)
• International Conference on Pattern Recognition 2024 (ICPR, CCF C)
• IEEE Signal Processing Letters (SPL)
• The 18th International Conference on Green, Pervasive, and Cloud Computing (GPC)

Serve as a program committee member for the following international conferences:

• The 16th International Conference on Creative Content Technologies (CONTENT)
• The 16th International Conference on Advances in Multimedia (MMEDIA)
• The 18th International Conference on Advances in Semantic Processing (SEMAPRO)

Honors & Awards

• [2024] Best Paper Award at the Academic Conference of the School of Computer Science and Technology
• [2023] Outstanding Graduate Student Communist Party Member Model Award.
• [2022] National Artificial Intelligence Security Competition, Excellence Award.
• [2022] National Scholarship for graduate students.
• [2022] Outstanding graduate student award.
• [2022] AAAI 2022 Data-Centric Robust Learning on ML Models, Twelfth Place Award.
• [2021] Outstanding student award.
• [2021] Second-Rank Academic Scholarship.
• [2021] Research and Innovation Scholarship.
• [2020] First-Rank Outstanding Student Scholarship.