| 神经网络水印综述 |
| |
| 引用本文： | 冯乐,朱仁杰,吴汉舟,张新鹏,钱振兴.神经网络水印综述[J].应用科学学报,2021,39(6):881-892. |
| |
| 作者姓名： | 冯乐 朱仁杰 吴汉舟 张新鹏 钱振兴 |
| |
| 作者单位： | 1. 复旦大学 计算机科学技术学院, 上海 200438;2. 上海大学 通信与信息工程学院, 上海 200444 |
| |
| 基金项目： | 国家自然科学基金（No.U1936214）资助 |
| |
| 摘 要： | 梳理了近年来神经网络水印技术的发展脉络,将主流方法大致归为白盒水印、黑盒水印、无盒水印和脆弱水印。综述了神经网络水印的评价指标和上述4种不同类型的神经网络水印技术,探讨了现有神经网络水印方案的优缺点,并对未来的发展趋势进行了展望。
|
| 关 键 词： | 神经网络 深度模型 数字水印 人工智能 |
| 收稿时间： | 2021-06-09 |
Survey of Neural Network Watermarking |
| |
| FENG Le,ZHU Renjie,WU Hanzhou,ZHANG Xinpeng,QIAN Zhenxing.Survey of Neural Network Watermarking[J].Journal of Applied Sciences,2021,39(6):881-892. |
| |
| Authors: | FENG Le ZHU Renjie WU Hanzhou ZHANG Xinpeng QIAN Zhenxing |
| |
| Institution: | 1. School of Computer Science, Fudan University, Shanghai 200438, China;2. College of Communication and Information Engineering, Shanghai University, Shanghai 200444, China |
| |
| Abstract: | This article sorts out the development context of neural network watermarking technology in recent years, and roughly classifies the mainstream methods into four categories, namely white box watermark, black box watermark, boxless watermark and fragile watermark. Specifically, this article reviews the evaluation indicators of neural network watermarking and these four different types of neural network watermarking technologies, discusses the advantages and disadvantages of existing neural network watermarking schemes, and looks forward to the future development trend. |
| |
| Keywords: | neural networks deep models digital watermark artificial intelligence |
|
| 点击此处可从《应用科学学报》浏览原始摘要信息 |
| 点击此处可从《应用科学学报》下载免费的PDF全文 |
|
