Adversarial attack-based security vulnerability verification using deep learning library for multimedia video surveillance
Adversarial attack-based security vulnerability verification using deep learning library for multimedia video surveillance
Jaehan Jeong,Sungmoon Kwon,2 Authors,Taeshik Shon
2019 · DOI: 10.1007/s11042-019-7262-8
Multimedia tools and applications · 23 Citations
TLDR
This study experimentally verified that classification accuracy in the image classification model of deep learning is lowered by adversarial samples generated by malicious attackers.