Department of Computer Science, College of Computers and Information Technology, Taif University, Taif 26571, Saudi Arabia.
Department of Computer Engineering, College of Computers and Information Technology, Taif University, Taif 26571, Saudi Arabia.
Sensors (Basel). 2023 Jan 27;23(3):1415. doi: 10.3390/s23031415.
Demand for data security is increasing as information technology advances. Encryption technology based on biometrics has advanced significantly to meet more convenient and secure needs. Because of the stability of face traits and the difficulty of counterfeiting, the iris method has become an essential research object in data security research. This study proposes a revolutionary face feature encryption technique that combines picture optimization with cryptography and deep learning (DL) architectures. To improve the security of the key, an optical chaotic map is employed to manage the initial standards of the 5D conservative chaotic method. A safe Crypto General Adversarial neural network and chaotic optical map are provided to finish the course of encrypting and decrypting facial images. The target field is used as a "hidden factor" in the machine learning (ML) method in the encryption method. An encrypted image is recovered to a unique image using a modernization network to achieve picture decryption. A region-of-interest (ROI) network is provided to extract involved items from encrypted images to make data mining easier in a privacy-protected setting. This study's findings reveal that the recommended implementation provides significantly improved security without sacrificing image quality. Experimental results show that the proposed model outperforms the existing models in terms of PSNR of 92%, RMSE of 85%, SSIM of 68%, MAP of 52%, and encryption speed of 88%.
随着信息技术的进步，对数据安全的需求不断增加。基于生物特征的加密技术已经取得了重大进展，以满足更加便捷和安全的需求。由于面部特征的稳定性和伪造的难度，虹膜方法已成为数据安全研究中必不可少的研究对象。本研究提出了一种将图像处理优化与密码学和深度学习（DL）架构相结合的革命性面部特征加密技术。为了提高密钥的安全性，采用光学混沌图来管理 5D 保守混沌方法的初始标准。提供安全的 Crypto 通用对抗神经网络和混沌光学地图来完成面部图像的加密和解密过程。目标字段用作加密方法中机器学习（ML）方法的“隐藏因素”。使用现代化网络将加密图像恢复为唯一图像，以实现图像解密。提供感兴趣区域（ROI）网络，以便从加密图像中提取相关项目，在受保护的隐私环境中更轻松地进行数据挖掘。本研究的结果表明，所提出的方案在不牺牲图像质量的情况下，显著提高了安全性。实验结果表明，所提出的模型在 PSNR 为 92%、RMSE 为 85%、SSIM 为 68%、MAP 为 52%和加密速度为 88%方面均优于现有模型。
