no code implementations • 8 Jun 2025 • Zhiyuan Zhong, Zhen Sun, Yepang Liu, Xinlei He, Guanhong Tao
Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers.
1 code implementation • 26 May 2025 • Ying Xiao, Jie Huang, Ruijuan He, Jing Xiao, Mohammad Reza Mousavi, Yepang Liu, Kezhi Li, Zhenpeng Chen, Jie M. Zhang
Large language models (LLMs) are reaching expert-level accuracy on medical diagnosis questions, yet their mistakes and the biases behind them pose life-critical risks.
1 code implementation • 8 Jun 2023 • Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, ZiHao Wang, XiaoFeng Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, Yang Liu
We deploy HouYi on 36 actual LLM-integrated applications and discern 31 applications susceptible to prompt injection.
no code implementations • 23 May 2023 • Ying Xiao, Shangwen Wang, Sicen Liu, Dingyuan Xue, Xian Zhan, Yepang Liu
The effectiveness and efficiency of these systems heavily depend on the quality of the training datasets.
1 code implementation • 9 Mar 2021 • Yue Liu, Chakkrit Tantithamthavorn, Li Li, Yepang Liu
In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment.
no code implementations • 24 Feb 2021 • Ying Wang, Liang Qiao, Chang Xu, Yepang Liu, Shing-Chi Cheung, Na Meng, Hai Yu, Zhiliang Zhu
The results showed that \textsc{Hero} achieved a high detection rate of 98. 5\% on a DM issue benchmark and found 2, 422 new DM issues in 2, 356 popular Golang projects.
Software Engineering
no code implementations • 6 Sep 2019 • Yongqiang Tian, Shiqing Ma, Ming Wen, Yepang Liu, Shing-Chi Cheung, Xiangyu Zhang
The corresponding rate for the object detection models is over 8. 5%.