Interpol review of detection of AI-generated image and video deepfakes, 2022-2025

In recent years, there has been tremendous progress in the generation of deepfakes and synthetic media. In this systematic review, we will, from a forensic perspective, discuss the latest developments in AI generation of deepfake images and videos and methods for detecting them. We analyzed more than 400 studies published between 2022 and 2025, specifically addressing the generation and detection of AI-generated deepfakes as opposed to manipulation of existing media. We provide an overview of the developments in various generative architectures such as GANs, diffusion models, and autoregressive models, highlighting progress in visual fidelity, user control, content consistency, and computational efficiency. In addition, we outline the most common designs of detection methods, looking at various types of features that are used for detection. We conclude that innovations are mainly centered on addressing the challenges of generalizability to unseen generators and robustness against common perturbations and adversarial attacks. However, the inconsistent use of the evaluation datasets makes it difficult to compare the methods. Our review has identified several directions for future research, such as making methods more directly applicable to forensic practice by incorporating forensically relevant benchmark datasets, paying more attention to explainability, and embedding detection methods in an evidence evaluation framework.