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

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.