Publications

(2024). On the Trustworthiness of Generative Foundation Models. In Working.

Project

Zhaoyi Liu, Huan Zhang (2024). Stealthy Backdoor Attack on Self-supervised Vision Encoders for Large Vision Language Models. In Conference on Computer Vision and Pattern Recognition (CVPR 2025, In Submission).

Cite

Dongping Chen, Ruoxi Chen, Shu Pu, Zhaoyi Liu, Yanru Wu, Caixi Chen, Benlin Liu, Yue Huang, Yao Wan, Pan Zhou, Ranjay Krishna (2024). Interleaved Scene Graph for Interleaved Text-and-Image Generation Assessment. In Thirteenth International Conference on Learning Representations (ICLR 2025, In Submission).

PDF Cite

Haichuan Zhang, Meiyu Lin, Zhaoyi Liu, Renyuan Li, Zhiyuan Cheng, Carl Yang, Mingjie Tang (2024). Attack as Defense: Run-time Backdoor Implantation for Image Content Protection. In Thirteenth International Conference on Learning Representations (ICLR 2025, In Submission).

Zhiyuan Cheng, Zhaoyi Liu, Tengda Guo, Shiwei Feng, Dongfang Liu, Mingjie Tang, Xiangyu Zhang (2024). BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks. In Forty-first International Conference on Machine Learning (ICML 2024).

PDF Cite Code

Xiaoda Wang, Zhaoyi Liu, Tengda Guo, Zhiyuan Cheng, Carl Yang, Mingjie Tang (2024). BadDet: Blockchain Fraud Detection with Dynamic Address-Transaction Graph Convolutional Networks. In ACM TheWebConf 2025 Conference (WWW 2025, In Submission).

Cite