The area of forgery detection of documents is considered an active field of research in digital forensics. One of the most common issues that investigators struggle with is circled around the selection of the approach in terms of accuracy, complexity, cost, and ease of use. The literature includes many approaches that are based on either image processing techniques or spectrums analysis. However, most of the available approaches have issues related to complexity and accuracy. This article suggests an unsupervised forgery detection framework that utilizes the correlations among the spectrums of documents’ matters in generating a weighted network for the tested documents. The network, then, is clustered using several unsupervised clustering algorithms. The detection rate is measured according to the number of network clusters. Based on the obtained results, our approach provides high accuracy using the Louvain clustering algorithms, while the use of the updated version of the DBSAN was more successful when testing many documents at the same time. Additionally, the suggested framework is considered simple to implement and does not require professional knowledge to use.

This article introduces a novel approach for forgery detection of documents based on the spectroscopy of documents' matters. The proposed approach uses concepts from network science to generate a weighted network of spectrums for both the original and questioned documents together. The nodes of the network represent the spectrums and the edges are the correlations among them. The detection method is based on the number of clusters obtained from the tested network using a modified version of the Louvain algorithm. The spectrums of the inks and papers that were used in printing the documents were obtained using Laser-Induced Breakdown Spectroscopy (LIBS) technology. The proposed approach was tested under variety of cases such as inkjet prints, laser prints, and different kinds of printing papers. It was also examined under several clustering algorithms. The findings showed that the approach always successful in distinguishing different kinds of documents with an accuracy of 100%. Moreover, the results of the proposed approach can be visually interpreted, which is more comfortable to investigators. Finally, the proposed approach is considered simple and does not need complex computations compared to the approaches in the literature.