We present INRSteg, an innovative lossless steganography framework based on a
novel data form Implicit Neural Representations (INR) that is modal-agnostic.
Our framework is considered for effectively hiding multiple data without
altering the original INR ensuring high-quality stego data. The neural
representations of secret data are first concatenated to have independent paths
that do not overlap, then weight freezing techniques are applied to the
diagonal blocks of the weight matrices for the concatenated network to preserve
the weights of secret data while additional free weights in the off-diagonal
blocks of weight matrices are fitted to the cover data. Our framework can
perform unexplored cross-modal steganography for various modalities including
image, audio, video, and 3D shapes, and it achieves state-of-the-art
performance compared to previous intra-modal steganographic methods.

INRSteg 是基于一种新颖的数据形式 Implicit Neural Representations (INR) 的创新无损隐写术框架，该框架适用于有效隐藏多个数据而不改变原始 INR，确保高质量的隐写数据，并能在图像、音频、视频和 3D 形状等多种模态中实现未开发的跨模态隐写术，与先前的内模态隐写方法相比，取得了最先进的性能。

通过隐式表示实现的灵活跨模态隐写术

Flexible Cross-Modal Steganography via Implicit Representations

Cross-modal Steganography is the practice of concealing secret signals in
publicly available cover signals (distinct from the modality of the secret
signals) unobtrusively. While previous approaches primarily concentrated on
concealing a relatively small amount of information, we propose THInImg, which
manages to hide lengthy audio data (and subsequently decode talking head video)
inside an identity image by leveraging the properties of human face, which can
be effectively utilized for covert communication, transmission and copyright
protection. THInImg consists of two parts: the encoder and decoder. Inside the
encoder-decoder pipeline, we introduce a novel architecture that substantially
increase the capacity of hiding audio in images. Moreover, our framework can be
extended to iteratively hide multiple audio clips into an identity image,
offering multiple levels of control over permissions. We conduct extensive
experiments to prove the effectiveness of our method, demonstrating that
THInImg can present up to 80 seconds of high quality talking-head video
(including audio) in an identity image with 160x160 resolution.

利用人脸特性，隐蔽地将较长的音频数据隐藏在身份图像中，实现 THInImg 的编码和解码方法，能够在 160x160 分辨率的身份图像中展示高质量的 80 秒说话头视频（包括音频）。

THInImg：面向图像中表述说话模型的跨模态隐写技术

THInImg: Cross-modal Steganography for Presenting Talking Heads in  Images

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.

本研究提出了一种基于深度学习的跨模态信息隐藏框架，使用隐式神经表征将多种格式的秘密数据嵌入到覆盖图像中，证明新的方法可扩展，能够容纳不同的模态。