Image Data Hiding in Neural Compressed Latent Representations
This work addresses image data hiding for applications requiring secrecy and robustness in compressed domains, representing an incremental improvement by combining data hiding with neural compression.
The paper tackles the problem of embedding and extracting secrets in neural compressed latent representations, achieving high image quality and bit accuracy while accelerating embedding speed by over 50 times compared to existing techniques.
We propose an end-to-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our proposed message encoder and decoder, our approach simultaneously achieves high image quality and high bit accuracy. Compared to existing techniques, our framework offers superior image secrecy and competitive watermarking robustness in the compressed domain while accelerating the embedding speed by over 50 times. These results demonstrate the potential of combining data hiding techniques and neural compression and offer new insights into developing neural compression techniques and their applications.