Cheng'an Wei

According to our database, Cheng'an Wei authored at least 5 papers between 2023 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Context Injection Attacks on Large Language Models.

Cheng'an Wei, Kai Chen, Yue Zhao, Yujia Gong, Lu Xiang, Shenchen Zhu

CoRR, 2024

AE-Morpher: Improve Physical Robustness of Adversarial Objects against LiDAR-based Detectors via Object Reconstruction.

Shenchen Zhu, Yue Zhao, Kai Chen, Bo Wang, Hualong Ma, Cheng'an Wei

Proceedings of the 33rd USENIX Security Symposium, 2024

LLM Factoscope: Uncovering LLMs' Factual Discernment through Measuring Inner States.

Jinwen He, Yujia Gong, Zijin Lin, Cheng'an Wei, Yue Zhao, Kai Chen

Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis.

Jinwen He, Yujia Gong, Kai Chen, Zijin Lin, Cheng'an Wei, Yue Zhao

CoRR, 2023

Aliasing Backdoor Attacks on Pre-trained Models.

Cheng'an Wei, Yeonjoon Lee, Kai Chen, Guozhu Meng, Peizhuo Lv

Proceedings of the 32nd USENIX Security Symposium, 2023