Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/213303
Title: Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
Authors: Weixuan Tang;Shunquan Tan;Bin Li;Jiwu Huang
Year: 2017
Publisher: IEEE
Abstract: Generative adversarial network has shown to effectively generate artificial samples indiscernible from their real counterparts with a united framework of two subnetworks competing against each other. In this letter, we first propose an automatic steganographic distortion learning framework using a generative adversarial network, which is composed of a steganographic generative subnetwork and a steganalytic discriminative subnetwork. Via alternately training these two oppositional subnetworks, our proposed framework can automatically learn embedding change probabilities for every pixel in a given spatial cover image. The learnt embedding change probabilities can then be converted to embedding distortions, which can be adopted in the existing framework of minimal-distortion embedding. Under this framework, the distortion function is directly related to the undetectability against the oppositional evolving steganalyzer. Experimental results show that with adversarial learning, our proposed framework can effectively evolve from nearly naive random &x00B1;1 embedding at the beginning to much more advanced content-adaptive embedding which tries to embed secret bits in textural regions. The security performance is also steadily improved with increasing training iterations.
URI: http://localhost/handle/Hannan/213303
volume: 24
issue: 10
More Information: 1547,
1551
Appears in Collections:2017

Files in This Item:
File SizeFormat 
8017430.pdf662.37 kBAdobe PDF
Title: Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
Authors: Weixuan Tang;Shunquan Tan;Bin Li;Jiwu Huang
Year: 2017
Publisher: IEEE
Abstract: Generative adversarial network has shown to effectively generate artificial samples indiscernible from their real counterparts with a united framework of two subnetworks competing against each other. In this letter, we first propose an automatic steganographic distortion learning framework using a generative adversarial network, which is composed of a steganographic generative subnetwork and a steganalytic discriminative subnetwork. Via alternately training these two oppositional subnetworks, our proposed framework can automatically learn embedding change probabilities for every pixel in a given spatial cover image. The learnt embedding change probabilities can then be converted to embedding distortions, which can be adopted in the existing framework of minimal-distortion embedding. Under this framework, the distortion function is directly related to the undetectability against the oppositional evolving steganalyzer. Experimental results show that with adversarial learning, our proposed framework can effectively evolve from nearly naive random &x00B1;1 embedding at the beginning to much more advanced content-adaptive embedding which tries to embed secret bits in textural regions. The security performance is also steadily improved with increasing training iterations.
URI: http://localhost/handle/Hannan/213303
volume: 24
issue: 10
More Information: 1547,
1551
Appears in Collections:2017

Files in This Item:
File SizeFormat 
8017430.pdf662.37 kBAdobe PDF
Title: Automatic Steganographic Distortion Learning Using a Generative Adversarial Network
Authors: Weixuan Tang;Shunquan Tan;Bin Li;Jiwu Huang
Year: 2017
Publisher: IEEE
Abstract: Generative adversarial network has shown to effectively generate artificial samples indiscernible from their real counterparts with a united framework of two subnetworks competing against each other. In this letter, we first propose an automatic steganographic distortion learning framework using a generative adversarial network, which is composed of a steganographic generative subnetwork and a steganalytic discriminative subnetwork. Via alternately training these two oppositional subnetworks, our proposed framework can automatically learn embedding change probabilities for every pixel in a given spatial cover image. The learnt embedding change probabilities can then be converted to embedding distortions, which can be adopted in the existing framework of minimal-distortion embedding. Under this framework, the distortion function is directly related to the undetectability against the oppositional evolving steganalyzer. Experimental results show that with adversarial learning, our proposed framework can effectively evolve from nearly naive random &x00B1;1 embedding at the beginning to much more advanced content-adaptive embedding which tries to embed secret bits in textural regions. The security performance is also steadily improved with increasing training iterations.
URI: http://localhost/handle/Hannan/213303
volume: 24
issue: 10
More Information: 1547,
1551
Appears in Collections:2017

Files in This Item:
File SizeFormat 
8017430.pdf662.37 kBAdobe PDF