Follow
Chengan Wei
Title
Cited by
Cited by
Year
Aliasing Backdoor Attacks on Pre-trained Models
C Wei, Y Lee, K Chen, G Meng, P Lv
32nd USENIX Security Symposium (USENIX Security 23), 2707-2724, 2023
42023
{AE-Morpher}: Improve Physical Robustness of Adversarial Objects against {LiDAR-based} Detectors via Object Reconstruction
S Zhu, Y Zhao, K Chen, B Wang, H Ma
33rd USENIX Security Symposium (USENIX Security 24), 7339-7356, 2024
12024
LLM Polygraph: Uncovering LLMs' Factual Discernment through Intermediate Data Analysis
J He, Y Gong, K Chen, Z Lin, C Wei, Y Zhao
arXiv preprint arXiv:2312.16374, 2023
12023
Hidden in Plain Sight: Exploring Chat History Tampering in Interactive Language Models
C Wei, Y Zhao, Y Gong, K Chen, L Xiang, S Zhu
arXiv preprint arXiv:2405.20234, 2024
2024
Adversarial Attack and Defense for Commercial Black-box Chinese-English Speech Recognition Systems
X Yuan, J Zhang, K Chen, C Wei, R Li, Z Ma, X Ling
ACM Transactions on Privacy and Security, 0
The system can't perform the operation now. Try again later.
Articles 1–5