ICASSP 2023accepted0 citations

HyperSteg: Hyperbolic Learning for Deep Steganography

Shivam Agarwal, Ritesh Soun, Rahul Shivani, Vishnu Varanasi, Navroop Gill, Ramit Sawhney

Abstract

Steganography is the art of hiding a secret message signal inside a publicly visible carrier with minimum perceptual loss in the carrier. In order to better hide information, it is critical to optimally represent the message-carrier wave interference while blending the message with the carrier. We propose HyperSteg: a novel steganography method in the hyperbolic space grounded in the hyperbolic properties of wave interference. Through hyperbolic learning, HyperSteg learns to better represent the hyperbolic properties of message-carrier interference with minimum additional computational cost. Through extensive experiments over image and audio datasets, we introduce HyperSteg as a practical, model and modality agnostic approach for information hiding.

BibTeX
@inproceedings{icassp2023_hypersteghyperbo,
  title = {HyperSteg: Hyperbolic Learning for Deep Steganography},
  author = {Shivam Agarwal and Ritesh Soun and Rahul Shivani and Vishnu Varanasi and Navroop Gill and Ramit Sawhney},
  booktitle = {ICASSP 2023},
  year = {2023}
}
HyperSteg: Hyperbolic Learning for Deep Steganography · ICASSP 2023