Deep learning-based Technique for Image Tamper Detection

Abstract

The objective of the research work is to thoroughly study existing methodologies for detecting passive image tampering using deep learning techniques. Here, survey is conducted predominantly focusing on tampering detection using deep learning techniques. Different image tampering datasets such as MICC, CASIA, and UCID, etc. have been used by existing tampering detection methodologies for validating tampering detection accuracies. From the study, it is identified that not all method obtains good accuracies for all kind of attack such as splicing, compression, rotation, resampling, copy-move, etc. From the study it is identified for detecting tampering efficiently it is important to design an efficient deep learning-based feature extraction mechanism that learns correlation among pixels more efficiently. In contrast with another recent survey, this paper covers significant developments in passive image forensic analysis methods adopting deep learning techniques. Existing methodologies are studied concerning benefit, limitation, the dataset used, and kind of attack considered. The paper further highlights future challenges and open issues, and also provides the possible future solution in building efficient tampering detection mechanism using deep learning technique. Experiment outcomes show good performance in connection with TPR, FPR, and F1-Score.