基于神经表征的深度跨模态隐写术
Deep Cross-Modal Steganography Using Neural Representations
AI总结:
针对现有深度隐写技术仅支持特定数据类型、无法实现跨模态隐写的问题,提出基于隐式神经表征的深度跨模态隐写框架,可将多格式多模态秘密数据隐藏于载体图像中,经多数据集验证具备良好可扩展性与模态适配能力。
摘要:
隐写术是将秘密数据嵌入到另一消息或数据中、使其不易被察觉的技术。随着深度学习的发展,深度神经网络(DNNs)近期已被应用于隐写领域。但现有深度隐写技术适用范围有限,仅聚焦特定数据类型,无法有效实现跨模态隐写。为此,我们提出一种基于隐式神经表征(Implicit Neural Representations, INRs)的深度跨模态隐写框架,可将多种格式的秘密数据隐藏在载体图像中。该框架利用INRs表征秘密数据,能够处理不同模态、不同分辨率的数据。在多种类型的不同秘密数据集上开展的实验表明,所提方法具备可扩展性,能够适配不同模态。
英文摘要:
Steganography is the process of embedding secret data into another message or data, in such a way that it is not easily noticeable. With the advancement of deep learning, Deep Neural Networks (DNNs) have recently been utilized in steganography. However, existing deep steganography techniques are limited in scope, as they focus on specific data types and are not effective for cross-modal steganography. Therefore, We propose a deep cross-modal steganography framework using Implicit Neural Representations (INRs) to hide secret data of various formats in cover images. The proposed framework employs INRs to represent the secret data, which can handle data of various modalities and resolutions. Experiments on various secret datasets of diverse types demonstrate that the proposed approach is expandable and capable of accommodating different modalities.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。