HUBFIRE - A multi-class SVM based JPEG steganalysis using HBCL statistics and FR Index


Downloads per month over past year

Bhat, V.H. and Krishna, S. and Deepa Shenoy, P. and Venugopal, K. and Patnaik, L.M. (2010) HUBFIRE - A multi-class SVM based JPEG steganalysis using HBCL statistics and FR Index. In: SECRYPT 2010 - Proceedings of the International Conference on Security and Cryptography, 26 July 2010 through 28 July 2010, Athens; Greece.


Download (1MB) | Preview
Official URL:


Blind Steganalysis attempts to detect steganographic data without prior knowledge of either the embedding algorithm or the 'cover' image. This paper proposes new features for JPEG blind steganalysis using a combination of Huffman Bit Code Length (HBCL) Statistics and File size to Resolution ratio (FR Index); the Huffman Bit File Index Resolution (HUBFIRE) algorithm proposed uses these functionals to build the classifier using a multi-class Support Vector Machine (SVM). JPEG images spanning a wide range of resolutions are used to create a 'stego-image' database employing three embedding schemes - the advanced Least Significant Bit encoding technique, that embeds in the spatial domain, a transform-domain embedding scheme: JPEG Hide-and-Seek and Model Based Steganography which employs an adaptive embedding technique. This work employs a multi-class SVM over the proposed 'HUBFIRE' algorithm for statistical steganalysis, which is not yet explored by steganalysts. Experiments conducted prove the model's accuracy over a wide range of payloads and embedding schemes.

Item Type: Conference or Workshop Item (Paper)
Additional Information: cited By 0; Conference of International Conference on Security and Cryptography, SECRYPT 2010 ; Conference Date: 26 July 2010 Through 28 July 2010; Conference Code:83484
Uncontrolled Keywords: A-transform; Adaptive embedding; Bit codes; Blind steganalysis; Embedding algorithms; Encoding techniques; File sizes; Functionals; Huffman; Huffman coding; JPEG image; Least significant bits; Model-based; Multi-class support vector machines; Multiclass SVM; Prior knowledge; Spatial domains; Statistical steganalysis; Steganalysis; Stego image; Support vector, Algorithms; Cryptography; Gears; Image coding; Steganography, Support vector machines
Subjects: Faculty of Engineering > Computer Science & Information Science Engineering
Divisions: University Visvesvarayya College of Engineering > Department of Computer Science and Information Science Engineering
Depositing User: Mr. Kirana Kumar D
Date Deposited: 17 Mar 2016 07:45
Last Modified: 17 Mar 2016 07:45

Actions (login required)

View Item View Item