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。