Mikołaj Płachta and Artur Janicki, Warsaw University of Technology, Poland
This paper addresses the problem of detecting image steganography based in JPEG files. We analyze the detection of the most popular steganographic algorithms: J-Uniward, UERD and nsF5, using DCTR, GFR and PHARM features. Our goal was to find a single neural network model that can best perform detection of different algorithms at different data hiding densities. We proposed a three-layer neural network in Dense-Batch Normalization architecture using ADAM optimizer. The research was conducted on the publicly available BOSS dataset. The best configuration achieved an average detection accuracy of 72 percent.
Steganography, deep machine learning, detection malware, BOSS database, image processing.