Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
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…
cs.CR2021
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…