Robust Data Hiding Using Inverse Gradient Attention

Data hiding is the procedure of encoding desired information into the cover image to resist potential noises while ensuring the embedded image has few perceptual perturbations from the original one. Recently, with the tremendous successes gained by deep neural networks in various fields, the researches of data hiding with deep learning models have attracted an increasing number of attentions. In the data hiding task, each pixel of cover images should be treated differently since they have divergent tolerabilities. The neglect of considering the sensitivity of each pixel will inevitably affect the model robustness for information hiding. Targeting this problem, we propose a novel deep data hiding scheme with Inverse Gradient Attention (IGA), combing the ideas of adversarial learning and attention mechanism to endow different sensitivities for different pixels. With the proposed component, the model can spotlight pixels with more robustness for data hiding. Empirically, extensive experiments show that the proposed model outperforms the state-of-the-art methods on two prevalent datasets under multiple evaluations. Besides, we further identify and discuss the connections between the proposed inverse gradient attention and high-frequency regions within images.