The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
Decoupled Neural Audio Steganography for Adaptive Sender-Side Model Updates
- Published
- Record updated
Summary
Existing neural audio steganography requires the sender and receiver to use paired, strictly synchronized models, which complicates deployment and increases leakage risk. The authors propose a synchronization-free framework built on decoupled neural embedding networks that follow a destruction-restoration principle: embedding is a destruction operation, and recovery uses a network from the audio restoration domain. The sender can upgrade, replace, or randomize the embedding network while the receiver still extracts the hidden message, and the authors report reliable extraction under these dynamic changes.