The field of image generation is rapidly evolving, with a growing focus on ensuring the authenticity and integrity of generated images. Researchers are exploring innovative methods to verify the origin and legitimacy of images, addressing concerns around deepfakes, copyright infringement, and data privacy. Notable advances include the development of robust watermarking techniques, auditing frameworks for data provenance, and forensic tools for identifying the source of manipulated images. These innovations have significant implications for various applications, including digital security, media integrity, and cultural preservation. Noteworthy papers include: A Watermark for Auto-Regressive Image Generation Models, which proposes a novel distortion-free watermarking method. GaussMarker: Robust Dual-Domain Watermark for Diffusion Models, which presents a dual-domain approach to watermarking diffusion models. FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakes, which introduces a lightweight framework for attributing face-swap deepfakes to their source models.