Low-Distortion Steganography in Neural Networks

In steganography, the cover medium takes on various types, including images, videos. Due to the advent of deep learning, neural network models are increasingly employed as the cover medium. In existing approaches, the embedding of secret data results in an obvious degradation of the model's original task performance, such as image classification. This paper proposes a low-distortion steganography method that embeds secret data into neural network models without degrading the model's original performance. The method selectively modifies parameters with minimal correlation to the loss function, ensuring that the model's performance remains unaffected. Furthermore, a suitable modification amplitude is defined to minimize the impact on task performance. Experimental results demonstrate that the proposed method enables low-distortion steganography while significantly improving embedding capacity and security. Notably, a maximum of 3.25 M bits of secret data is successfully embedded into a VGG model on the MNIST dataset, resulting in less than 0.1% accuracy degradation, a significant improvement over previous methods.