文献类型：期刊文献

英文题名：Hide and Recognize Your Privacy Image

作者：Zhu, Zhiying[1];Zhou, Hang[2];Hu, Haoqi[3];Jiang, Qingchao[1];Qian, Zhenxing[3];Zhang, Xinpeng[3]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Simon Fraser Univ, Dept Sch Comp Sci, Burnaby, BC V5A 1S6, Canada;[3]Fudan Univ, Dept Sch Comp Sci, Shanghai 200433, Peoples R China

年份：2024

卷号：11

期号：6

起止页码：6130

外文期刊名：IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING

收录：;EI(收录号：20243817054985);WOS:【SCI-EXPANDED(收录号:WOS:001360482400038)】；

基金：This work was supported by the National Natural Science Foundation of China under Grant 62402182 and Grant U20B2051.

语种：英文

外文关键词：Data security; image recognition; privacy protection; privacy protection; image recognition; privacy protection

摘要：Recent studies have demonstrated that deep neural networks show excellent performance in information hiding. Considering the tremendous progress that deep learning has made in image recognition, we explore whether neural networks can recognize invisible private images hidden in cover images. In this article, we propose a method for image recognition in the covert domain using neural networks. Our target is to hide an image inside another image with minimal visual quality loss, while at the same time, the hidden image can be recognized correctly without being recovered. In the proposed system, the hiding and recognition of secret images are all performed by neural networks. The hiding network and the recognition network are designed to specifically work as a pair. We design and jointly train preparation, hiding, and recognition networks, where given a cover and a secret image, the preparation network reduces redundant information of the secret image, the hiding network produces a stego image that is visually indistinguishable from the cover image, and the PSNR and SSIM reach 38.5 dB and 0.991 on the MNIST & CIFAR-10 dataset and 41.8 dB and 0.995 on the CelebA & Scene dataset, respectively. The recognition network can correctly identify the secret image inside the stego image which reaches 98.3% recognition accuracy on MNIST dataset and 91.6% recognition accuracy on CelebA dataset in the covert domain, less than 1% recognition decrease compared with direct recognition. In summary, our approach can successfully identify the secret image without revealing its content. Across various datasets, both the classification accuracy and the invisibility of private images are consistently satisfactory.