Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Approaching Optimal Embedding in Audio Steganography with GAN

Abstract: 

Audio steganography is a technology that embeds messages into audio without raising any suspicion from hearing it. Current steganography methods are based on heuristic cost designs. In this work, we proposed a framework based on Generative Adversarial Network (GAN) to approach optimal embedding for audio steganography in the temporal domain. This is the first attempt to approach optimal embedding with GAN and automatically learn the embedding probability/cost for audio steganography. The embedding framework consists of three parts: a U-Net based generator, an embedding simulator, and a discriminator. For practical applications, Syndrome-Trellis Coding (STC) is used to generate stego audio with the learned embedding probability. Experimental results on the UME-ERJ and WSJ speech datasets have shown that the proposed framework can automatically learn the adaptive embedding probabilities for audio steganogra- phy and has a considerable advantage in terms of resisting steganalyzers in comparison with the existing conventional method.

up
0 users have voted:

Paper Details

Authors:
Jianhua Yang, Huilin Zheng, Xiangui Kang, Yun-Qing Shi
Submitted On:
28 May 2020 - 10:39pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Huilin Zheng
Paper Code:
2093
Document Year:
2020
Cite

Document Files

icassp2020_2093.pdf

(59)

Subscribe

[1] Jianhua Yang, Huilin Zheng, Xiangui Kang, Yun-Qing Shi, "Approaching Optimal Embedding in Audio Steganography with GAN", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5445. Accessed: Sep. 26, 2020.
@article{5445-20,
url = {http://sigport.org/5445},
author = {Jianhua Yang; Huilin Zheng; Xiangui Kang; Yun-Qing Shi },
publisher = {IEEE SigPort},
title = {Approaching Optimal Embedding in Audio Steganography with GAN},
year = {2020} }
TY - EJOUR
T1 - Approaching Optimal Embedding in Audio Steganography with GAN
AU - Jianhua Yang; Huilin Zheng; Xiangui Kang; Yun-Qing Shi
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5445
ER -
Jianhua Yang, Huilin Zheng, Xiangui Kang, Yun-Qing Shi. (2020). Approaching Optimal Embedding in Audio Steganography with GAN. IEEE SigPort. http://sigport.org/5445
Jianhua Yang, Huilin Zheng, Xiangui Kang, Yun-Qing Shi, 2020. Approaching Optimal Embedding in Audio Steganography with GAN. Available at: http://sigport.org/5445.
Jianhua Yang, Huilin Zheng, Xiangui Kang, Yun-Qing Shi. (2020). "Approaching Optimal Embedding in Audio Steganography with GAN." Web.
1. Jianhua Yang, Huilin Zheng, Xiangui Kang, Yun-Qing Shi. Approaching Optimal Embedding in Audio Steganography with GAN [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5445