AI-Generated Image Detection
Overview
The field studies how to distinguish authentic photographs and artwork from fully generated images and AI-edited content, sometimes also locating altered regions or identifying the source generator. Detectors use visual artifacts such as noise, color and frequency patterns, and local texture, as well as features from pretrained vision models; other approaches compare images with reconstructions or perturbations, or combine several detectors. Researchers evaluate these methods on cross-generator and cross-dataset benchmarks, including tests with compression, resizing, and other real-world changes, and increasingly on specialized content such as documents and scientific figures. A central challenge is that strong results on familiar, clean benchmarks often fail to transfer to new generators or settings, while improving sensitivity can raise false alarms on genuine images.
Latest papers
193 papers21 papers in the last four weeks, up 50% on the four weeks before. 0.1% of all new papers.