A new approach to compressed file fragment identification

Abstract

Identifying the underlying type of a file given only a file fragment is a big challenge in digital forensics. Many methods have been applied to file type identification; however the identification accuracies of most of file types are still very low, especially for files having complex structures because their contents are compound data built from different data types. In this paper, we propose a new approach based on the deflate-encoded data detection, entropy-based clustering, and the use of machine learning techniques to identify deflate-encoded file fragments. Experiments on the popular compound file type showed high identification accuracy for the proposed method.