3 papers
cs.CV2024
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
Sheng Yang, Jiawang Bai, Kuofeng Gao +3
Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tas…
cs.PL2023
Context Sensitivity without Contexts: A Cut-Shortcut Approach to Fast and Precise Pointer Analysis
Wenjie Ma, Shengyuan Yang, Tian Tan +3
Over the past decades, context sensitivity has been considered as one of the most effective ideas for improving the precision of pointer analysis for Java. However, despite great p…
cs.CV2022
Backdoor Defense via Suppressing Model Shortcuts
Sheng Yang, Yiming Li, Yong Jiang +1
Recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks during the training process. Specifically, the adversaries intend to embed hidd…