首页|基于隐式神经表示的模型隐写方案

基于隐式神经表示的模型隐写方案

扫码查看
可视数据(图像、视频、3D模型)的隐式表达已经成为当前计算机视觉研究的热点,提出了一种新的基于隐式神经表示的模型隐写方案,消息发送方利用神经辐射场(neural radiance fields,NeRF)新视角合成的特性,通过引入一个视角作为密钥,由NeRF模型生成秘密视角图像作为后门,然后利用过拟合的方法训练一个消息提取器,以建立秘密消息和秘密视角图像的一一映射.发送方将训练好的NeRF模型和消息提取器通过公开信道传递给接收方,接收方利用双方共享的密钥,由NeRF模型获得秘密视角下的渲染图像,再通过消息提取器获得秘密消息.而攻击方因无法准确掌握该视角信息,从而无法窃取秘密消息.实验结果证明:所训练的消息提取器实现大容量快速隐写,消息嵌入量达100%,同时NeRF巨大的视角密钥空间保证了该方案的隐蔽性.
Model Steganography with Implicit Neural Representation
The utilization of implicit representation for visual data(such as images,videos,and 3 D models)had recently gained significant attention in computer vision research.A novel model steganography scheme with implicit neural representation was pro-posed.In this scheme,the message sender leveraged neural radiance fields(NeRF)and its viewpoint synthesis capabilities by introdu-cing a viewpoint as a key.The NeRF model generated a secret viewpoint image,which served as a backdoor.Subsequently,a message extractor was trained using overfitting to establish a one-to-one mapping between the secret message and the secret viewpoint image.To transmit the secret message,the sender sent both the trained NeRF model and the message extractor to the receiver through an open communication channel.The receiver employed the shared key to obtain the rendered image from the NeRF model in the secret view-point.Consequently,the secret message was extracted by the message extractor.The inherent complexity of the viewpoint information prevented attackers from stealing the secret message accurately.Experimental results demonstrate that the message extractor trained achieves high-capacity steganography with fast performance,achieving a 100%message embedding.Furthermore,the extensive view-point key space of NeRF ensures the security of the steganography scheme.

data hidingimplicit neural expressionneural radiance fieldmodel steganographymessage extractor

董炜娜、刘佳、孙文权、陈立峰、潘晓中、柯彦

展开 >

武警工程大学网络与信息安全武警部队重点实验室,西安 710086

武警工程大学密码工程学院,西安 710086

信息隐藏 隐式神经表示 神经辐射场 模型隐写 消息提取器

国家自然科学基金面上项目国家自然科学基金国家自然科学基金科技创新团队创新研究项目

622724786187238462102450ZZKY20222102

2024

科学技术与工程
中国技术经济学会

科学技术与工程

CSTPCD北大核心
影响因子:0.338
ISSN:1671-1815
年,卷(期):2024.24(25)