Liu Bo, Zheng XingYi, Verma Dharmendra, Zhao Yudi, Liang Hanyuan, Li Lain-Jong, Chen Jenhui, Lai Chao-Sung
Faculty of Information Technology, College of Microelectronics, Beijing University of Technology, Beijing 100124, People's Republic of China.
Department of Computer Science and Information Engineering, Chang Gung University, Guishan Dist., Taoyuan City 33302, Taiwan.
ACS Appl Mater Interfaces. 2023 Oct 25;15(42):49478-49486. doi: 10.1021/acsami.3c10106. Epub 2023 Oct 12.
In the emerging technology, the generative aversive networks (GANs), randomness, and unpredictability of inputting noises are the keys to the uniqueness, diversity, robustness, and security of the generated images. Compared with deterministic software-based noise generation, hardware-based noise generation introduces physical entropy sources, such as electronic and photonic noises, to add unpredictability. In this study, bimode BiOSe-based noise generators have been demonstrated for the application of GANs. Harnessing its ultrahigh carrier mobility, excellent air stability, marvelous optoelectronic performance, as well as the unique surface resistive switching effect and defect locations in the energy diagram, BiOSe provides a good material platform to easily integrate with multiple device architectures for generating noises in different physical sources. The noise of the black current mode in a photodetector architecture and the random telegraph noise in a memristor mode were measured, characterized, compared, and analyzed. A method of Markov chain equipped with K-means clustering was carried out to calculate the discrete noise states and the transition probability matrix between them. To evaluate the generated properties of the GANs based on the hardware noise source, the inception score and Fréchet inception distance were evaluated.
在新兴技术生成对抗网络（GANs）中，输入噪声的随机性和不可预测性是生成图像独特性、多样性、鲁棒性和安全性的关键。与基于确定性软件的噪声生成相比，基于硬件的噪声生成引入了物理熵源，如电子和光子噪声，以增加不可预测性。在本研究中，已展示了基于双模式BiOSe的噪声发生器在GANs中的应用。利用其超高的载流子迁移率、优异的空气稳定性、出色的光电性能，以及独特的表面电阻开关效应和能带图中的缺陷位置，BiOSe提供了一个良好的材料平台，可轻松与多种器件架构集成，以在不同物理源中生成噪声。对光电探测器架构中暗电流模式的噪声和忆阻器模式中的随机电报噪声进行了测量、表征、比较和分析。采用了一种配备K均值聚类的马尔可夫链方法来计算离散噪声状态及其之间的转移概率矩阵。为了评估基于硬件噪声源的GANs的生成特性，对初始得分和弗雷歇初始距离进行了评估。
