Rapid detection of stego images based on identifiable features

An increasing number of images in the Internet brings forward a higher requirement on the speed of steganalysis. For the problem of real-time detection of stego images, a method of images steganalysis rapidly based on identifiable features is proposed, where the identifiable features are specific character sequences left in stego images by steganography tools. According to finding whether an image contains these features can judge reliably the image is stego or cover. Meanwhile, for multiple identifiable features appearing on the same location of an image, an algorithm of identifiable features recognized based on AC (Aho-Corasick) multi-features matching algorithm is proposed, which can improve the detection speed. Experiment shows that the steganalysis method proposed can achieve a perfect detection precision, and the detection speed can be improved significantly comparing with traditional methods (matching bytes one by one).

[1]  Yeuan-Kuen Lee,et al.  A Method for Automatic Identification of Signatures of Steganography Software , 2010, IEEE Transactions on Information Forensics and Security.

[2]  Niels Provos,et al.  Defending Against Statistical Steganalysis , 2001, USENIX Security Symposium.

[3]  Jessica J. Fridrich,et al.  Rich Models for Steganalysis of Digital Images , 2012, IEEE Transactions on Information Forensics and Security.

[4]  Jessica J. Fridrich,et al.  Steganalysis of JPEG images using rich models , 2012, Other Conferences.

[5]  Andreas Westfeld,et al.  F5-A Steganographic Algorithm , 2001, Information Hiding.

[6]  Tomás Pevný,et al.  Merging Markov and DCT features for multi-class JPEG steganalysis , 2007, Electronic Imaging.

[7]  Andreas Westfeld,et al.  F5—A Steganographic Algorithm High Capacity Despite Better Steganalysis , 2001 .

[8]  Jessica J. Fridrich,et al.  Feature-Based Steganalysis for JPEG Images and Its Implications for Future Design of Steganographic Schemes , 2004, Information Hiding.

[9]  John McHugh,et al.  A cautionary note on image downgrading , 1992, [1992] Proceedings Eighth Annual Computer Security Application Conference.

[10]  Phil Sallee,et al.  Model-Based Steganography , 2003, IWDW.

[11]  Liu Yan-bing,et al.  Charactering memory access behavior of large scale multi-string matching algorithms , 2007 .

[12]  Tomás Pevný,et al.  Statistically undetectable jpeg steganography: dead ends challenges, and opportunities , 2007, MM&Sec.

[14]  Divyakant Agrawal,et al.  An efficient and fault-tolerant solution for distributed mutual exclusion , 1991, TOCS.

[15]  Dana S. Richards,et al.  Modified Matrix Encoding Technique for Minimal Distortion Steganography , 2006, Information Hiding.

[16]  FridrichJessica,et al.  Rich Models for Steganalysis of Digital Images , 2012 .

[17]  W. Marsden.  I and J , 2012 .

[18]  Nhat-Phuong Tran,et al.  High performance string matching for security applications , 2013, International Conference on ICT for Smart Society.

[19]  Jessica J. Fridrich,et al.  Further study on the security of S-UNIWARD , 2014, Electronic Imaging.

[20]  Vijay Rana,et al.  MBSOM: An agent based semantic ontology matching technique , 2015, 2015 International Conference on Futuristic Trends on Computational Analysis and Knowledge Management (ABLAZE).

[21]  Fenlin Liu,et al.  Recognizing F5-like Stego images from Multi-class JPEG Stego Images , 2014, KSII Trans. Internet Inf. Syst..

[22]  Tomás Pevný,et al.  Using High-Dimensional Image Models to Perform Highly Undetectable Steganography , 2010, Information Hiding.

[23]  Tomás Pevný,et al.  Steganographic key leakage through payload metadata , 2014, IH&MMSec '14.

[24]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[25]  Jiwu Huang,et al.  Edge Adaptive Image Steganography Based on LSB Matching Revisited , 2010, IEEE Transactions on Information Forensics and Security.