Steganographer detection via deep residual network

Zheng, Mingjie; Zhang, Shenghua; Wu, Songtao; Jiang, Jianmin

doi:10.1109/icme.2017.8019320

Cited by 12 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the steganography techniques could be maliciously used for stealing confidential information, it is practically significant to carry on researches to forensics of the crime. For decades, researchers have proposed many techniques for the forensics of steganography, including the stego detection [2][3][4][5][6][7][8][9][10], the payload location [11][12][13][14][15], the embedding key restore [16,17], the secret message extraction [17], and the steganographer detection [18][19][20]. In practice, the covert communication entity on the Internet usually acts as the user of social platforms, whose location is virtual.…”

Section: Introductionmentioning

confidence: 99%

Geolocation of covert communication entity on the Internet for post-steganalysis

Zhang

Liu

Luo

2020

J Image Video Proc.

View full text Add to dashboard Cite

Geolocation of covert communication entity is significantly important for the forensics of the crime but has significant challenges when the steganalyst locks the guilty actor IP and wants to know the physical location of the actor. This kind of post-steganalysis involves not only the stegos transmitted on the Internet but the IP package head and content. This paper presents a geolocation method for the location of the covert communication entity based on hophot path coding. The method estimates the location of the covert communication entity by combining the path and delay between probes and the covert communication entity IP, which improves the deficiency that similar delays do not necessarily mean close geographical locations of the IPs. Moreover, the similarity between the IPs' paths can be measured by coding the paths between IPs and probes. The results of a series of experiments show that the median error of the proposed method is within 6.16 km using different thresholds.

show abstract

Section: Introductionmentioning

confidence: 99%

Geolocation of covert communication entity on the Internet for post-steganalysis

Zhang

Liu

Luo

2020

J Image Video Proc.

View full text Add to dashboard Cite

show abstract

“…More generally, we hope that this research will stimulate practical approaches to detecting a steganographer amongst multiple actors. This is an area which has relatively little attention [12,15], compared with binary detection applied to a single image. Just as the single-actor, single-image Square-Root Law -a theoretical result about unrealistic probabilistic models -has been observed robustly in genuine image steganography [7], we predict that a welldesigned steganographer detector should exhibit the O( log K) law derived here.…”

Section: Discussionmentioning

confidence: 99%

Capacity Laws for Steganography in a Crowd

Ker

2022

Proceedings of the 2022 ACM Workshop on Information Hiding and Multimedia Security

View full text Add to dashboard Cite

A steganographer is not only hiding a payload inside their cover, they are also hiding themselves amongst the non-steganographers.In this paper we study asymptotic rates of growth for steganographic data -analogous to the classical Square-Root Law -in the context of a 'crowd' of K actors, one of whom is a steganographer. This converts steganalysis from a binary to a K-class classification problem, and requires some new information-theoretic tools. Intuition suggests that larger K should enable the steganographer to hide a larger payload, since their stego signal is mixed in with larger amounts of cover noise from the other actors. We show that this is indeed the case, in a simple independent-pixel model, with payload growing at O( log K) times the classical Square-Root capacity in the case of homogeneous actors. Further, examining the effects of heterogeneity reveals a subtle dependence on the detector's knowledge about the payload size, and the need for them to use negative as well as positive information to identify the steganographer. CCS CONCEPTS• Security and privacy → Information-theoretic techniques;• Mathematics of computing → Coding theory.

show abstract

“…Proposed network can obtain remarkable performance boost compared to DCTR [39], but still inferior to PHARM. In the same year Xu et al [21], construct a deep learning neural network with 20-layers for JPEG steganalysis, strongly inspired by Res-Net [52] with shortcut connection tricks [21]. Proposed network replaced pooling layers with convolutional layers also improved the result in terms of accuracy.…”

Section: Jpeg Image Steganalysismentioning

confidence: 99%

A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis

2020

KSII TIIS

View full text Add to dashboard Cite

Steganalysis & steganography have witnessed immense progress over the past few years by the advancement of deep convolutional neural networks (DCNN). In this paper, we analyzed current research states from the latest image steganography and steganalysis frameworks based on deep learning. Our objective is to provide for future researchers the work being done on deep learning-based image steganography & steganalysis and highlights the strengths and weakness of existing up-to-date techniques. The result of this study opens new approaches for upcoming research and may serve as source of hypothesis for further significant research on deep learning-based image steganography and steganalysis. Finally, technical challenges of current methods and several promising directions on deep learning steganography and steganalysis are suggested to illustrate how these challenges can be transferred into prolific future research avenues.

show abstract

Steganographer detection via deep residual network

Cited by 12 publications

References 18 publications

Geolocation of covert communication entity on the Internet for post-steganalysis

Geolocation of covert communication entity on the Internet for post-steganalysis

Capacity Laws for Steganography in a Crowd

A Survey on Deep Convolutional Neural Networks for Image Steganography and Steganalysis

Contact Info

Product

Resources

About