Universal Perturbation-based Secret Key-Controlled Data Hiding. (arXiv:2311.01696v1 [cs.CR])

Deep neural networks (DNNs) are demonstrated to be vulnerable to universal
perturbation, a single quasi-perceptible perturbation that can deceive the DNN
on most images. However, the previous works are focused on using universal
perturbation to perform adversarial attacks, while the potential usability of
universal perturbation as data carriers in data hiding is less explored,
especially for the key-controlled data hiding method. In this paper, we propose
a novel universal perturbation-based secret key-controlled data-hiding method,
realizing data hiding with a single …

adversarial adversarial attacks attacks carriers data images key networks neural networks secret secret key single usability vulnerable