Detection of StegoBot
V. Natarajan, Shina Sheen, R. Anitha · 2012
StegoBot is a recently discovered social network security threat that allows probabilistically unobservable communication through social network. The main aim of a Stegobot is to spread social malware and steal the information from targeted machines. Stegobot takes the advantage of image Steganography to hide the presence of communication within the image sharing behavior of user interaction. In this paper, we present a detection scheme to detect StegoBot. We analyzed different entropies of images to show that image files are generally very sensitive to embedding. Ensemble classification is employed here as a powerful tool that allows fast detection of StegoBot. The power of the proposed framework is demonstrated on different social networks with different evaluation metrics.