Statistical methods for digital image forensics: Algorithm mismatch for blind spatial steganalysis and score-based likelihood ratios for camera device identification

Abstract

The number and availability of steganographic embedding algorithms continues to grow. Many traditional blind steganalysis frameworks require training examples from every embedding algorithm, but collecting, storing and processing representative examples of each algorithm can quickly become untenable. Our motivation for this paper is to create a straight-forward, non-data-intensive framework for blind steganalysis that only requires examples of cover images and a single embedding algorithm for training. Our blind steganalysis framework addresses the case of algorithm mismatch, where a classifier is trained on one algorithm and tested on another, with four spatial embedding algorithms: LSB matching, MiPOD, S-UNIWARD and WOW. We use RAW image data from the BOSSbase Database and and six iPhone devices collected for the StegoAppDB project. Ensemble Classifiers with Spatial Rich Model features are trained on a single embedding algorithm and tested on each of the four algorithms. Classifiers trained on MiPOD, S-UNIWARD and WOW data achieve decent error rates when testing on all four algorithms. Most notably, an Ensemble Classifier with an adjusted decision threshold trained on LSB matching data achieves decent detection results on MiPOD, S-UNIWARD and WOW data.

Source‐anchored, trace‐anchored, and general match score‐based likelihood ratios for camera device identification

“…van Houten et al performed experiments on two camera models: the Motorola V360 mobile phone camera (10 cameras) and the Sony DSC‐S500 camera (nine cameras). Reinders [36] and Reinders et al [37] adapted the method Hepler et al used to calculate trace‐anchored SLRs for the camera device identification problem. We present an extended investigation of the use of SLRs for camera device identification beyond the current published literature and develop a framework for calculating all three available types of specific‐source SLRs with a larger dataset of 48 camera devices from 26 distinct camera models.…”