Audio Steganography Based on Iterative Adversarial Attacks Against Convolutional Neural Networks

摘要

Recently, convolutional neural networks (CNNs) have demonstrated superior performance on digital multimedia steganalysis. However, some studies have noted that most CNN-based classifiers can be easily fooled by adversarial examples, which form slightly perturbed inputs to a target network according to the gradients. Inspired by this phenomenon, we first introduce a novel steganography method based on adversarial examples for digital audio in the time domain. Unlike related methods for image steganography, such as which are highly dependent on some existing embedding costs, the proposed method can start from a flat or even a random embedding cost and then iteratively update the initial costs by exploiting the adversarial attacks until satisfactory security performances are obtained. The extensive experimental results show that our method significantly outperforms the existing nonadaptive and adaptive steganography methods and achieves state-of-the-art results. Moreover, we also provide experimental results to investigate why the proposed embedding modifications seem evenly located at all audio segments despite their different content complexities, which is contrary to the content adaptive principle widely employed in modern steganography methods.