Digital Forensic on Image Manipulation Crime - A Systematic Literature Review

Image manipulation crimes have become increasingly common due to the widespread use of advanced digital devices and social media. These crimes involve altering digital images to deceive, defraud, or cause harm, with significant implications for privacy, security, and trust. As images can be easily manipulated and disseminated online, it has become easier for malicious actors to spread misinformation, steal personal information, and commit fraud. This highlights the urgent need for robust detection and prevention methods. Verifying the authenticity of images, known as digital image forensics, is essential. Forensic methods used for image analysis include metadata analysis, frame analysis, and pixel analysis. Leveraging these methods is expected to offer solutions for tackling image manipulation; however, their implementation presents several challenges. The objective of this study is to apply the Systematic Literature Review (SLR) methodology to explore the challenges in digital image forensics related to image manipulation from the last five years (2018–2023) that remain unaddressed. Through the SLR method, research papers were identified using the IEEE Xplore Digital Library, following established inclusion and exclusion criteria. From an initial pool of 246 journals, 26 were selected for detailed investigation. The literature review shows that research in this field continues to grow, with 26 distinct methods identified. The three most common methods are Convolutional Neural Networks (CNN), Blockchain Technology, and Machine Learning. The results of this study provide valuable insights into current research trends and can serve as a guide for future studies in this evolving field.