4 papers
Known Meets Unknown: Mitigating Overconfidence in Open Set Recognition
Dongdong Zhao, Ranxin Fang, Changtian Song +2
Open Set Recognition (OSR) requires models not only to accurately classify known classes but also to effectively reject unknown samples. However, when unknown samples are semantica…
Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
Baogang Song, Dongdong Zhao, Jianwen Xiang +2
Backdoor attacks pose a persistent security risk to deep neural networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning…
NegDL: Privacy-Preserving Deep Learning Based on Negative Database
Dongdong Zhao, Pingchuan Zhang, Jianwen Xiang +1
In the era of big data, deep learning has become an increasingly popular topic. It has outstanding achievements in the fields of image recognition, object detection, and natural la…
Using Context Information to Enhance Simple Question Answering
Lin Li, Mengjing Zhang, Zhaohui Chao +1
With the rapid development of knowledge bases(KBs),question answering(QA)based on KBs has become a hot research issue. In this paper,we propose two frameworks(i.e.,pipeline framewo…