Whispering to DNN: A Speech Steganographic Scheme Based on Hidden Adversarial Examples for Speech Recognition Models

Recently, adversarial-examples-based audio steganography was proposed, which hid the messages by generating audio adversarial examples whose target phrases are the hidden messages. However, the embedding operation causes noticeable distortion, and the form of the hidden message must be a sentence or a phrase, which limits the application of steganography. In this paper, we propose a novel steganography based on the hidden adversarial example (HAE) that is similar to a normal input but will get the hidden-message-encoded logits after passing through the neural network. In the HAE-based steganography, the message is embedded by adding slight noise to audios to modify the maximum logit of each frame to particular intervals. The experimental results show that the stego audios generated by HAE-based steganography are more concealed and own better speech quality.