Jiangchuan Li, Peisong He*, Jiayong Liu, Jie Luo, Qiang Xia
CMC-Computers, Materials & Continua, Vol.75, No.3, pp. 4893-4915, 2023, DOI:10.32604/cmc.2023.036819
Abstract Steganography techniques, such as audio steganography, have been widely used in covert communication. However, the deep neural network, especially the convolutional neural network (CNN), has greatly threatened the security of audio steganography. Besides, existing adversarial attacks-based countermeasures cannot provide general perturbation, and the transferability against unknown steganography detection methods is weak. This paper proposes a cover enhancement method for audio steganography based on universal adversarial perturbations with sample diversification to address these issues. Universal adversarial perturbation is constructed by iteratively optimizing adversarial perturbation, which applies adversarial attack techniques, such as Deepfool. Moreover, the sample diversification strategy is designed to improve… More >
Login
Register
