SIA-GAN: Scrambling Inversion Attack Using Generative Adversarial Network

SIA-GAN: Scrambling Inversion Attack Using Generative Adversarial Network

This paper presents a scrambling inversion attack using a generative adversarial network (SIA-GAN). This method aims to evaluate the privacy protection level achieved by image scrambling method. For privacy-preserving machine learning, scrambled images are often used to protect visual information, a...

Full description

Bibliographic Details
Main Authors: Koki Madono, Masayuki Tanaka, Masaki Onishi, Tetsuji Ogawa
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Artificial intelligence
machine learning
computer vision
visual information hiding
image scrambling
Online Access:https://ieeexplore.ieee.org/document/9537763/

Internet

https://ieeexplore.ieee.org/document/9537763/

Similar Items