The field of image forgery detection and localization is rapidly advancing, with a focus on developing more robust and generalizable methods. Recent research has highlighted the importance of addressing vulnerabilities in foundation models, such as the Segment Anything Model (SAM), and developing techniques to detect and localize image forgeries in a unified and scalable manner. Notable developments include the use of diffusion models, low-rank adaptation, and semantic-aware reconstruction error to improve detection and localization performance. These advancements have significant implications for digital forensics and the protection of individuals' portrait rights and privacy. Noteworthy papers include: UGD-IML, which proposes a unified generative framework for constrained and unconstrained image manipulation localization. CLUE, which leverages low-rank adaptation to capture latent uncovered evidence for image forgery localization. ForensicsSAM, which presents a unified image forgery detection and localization framework with built-in adversarial robustness. RelayFormer, which introduces a unified local-global attention framework for scalable image and video manipulation localization. SARE, which proposes a semantic-aware reconstruction error for generalizable diffusion-generated image detection.