{"ID":2860324,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.04225","arxiv_id":"2510.04225","title":"Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images","abstract":"The rapid growth of AI-generated imagery has blurred the boundary between real and synthetic content, raising practical concerns for digital integrity. Vision-language models (VLMs) can provide natural language explanations, but standard one-pass classifiers often miss subtle artifacts in high-quality synthetic images and offer limited grounding in the pixels. We propose Locate-Then-Examine (LTE), a two-stage VLM-based forensic framework that first localizes suspicious regions and then re-examines these crops together with the full image to refine the real vs. AI-generated verdict and its explanation. LTE explicitly links each decision to localized visual evidence through region proposals and region-aware reasoning. To support training and evaluation, we introduce TRACE, a dataset of 20,000 real and high-quality synthetic images with region-level annotations and automatically generated forensic explanations, constructed by a VLM-based pipeline with additional consistency checks and quality control. Across TRACE and multiple external benchmarks, LTE achieves competitive accuracy and improved robustness while providing human-understandable, region-grounded explanations suitable for forensic deployment.","short_abstract":"The rapid growth of AI-generated imagery has blurred the boundary between real and synthetic content, raising practical concerns for digital integrity. Vision-language models (VLMs) can provide natural language explanations, but standard one-pass classifiers often miss subtle artifacts in high-quality synthetic images...","url_abs":"https://arxiv.org/abs/2510.04225","url_pdf":"https://arxiv.org/pdf/2510.04225v2","authors":"[\"Yikun Ji\",\"Yan Hong\",\"Bowen Deng\",\"Jun Lan\",\"Huijia Zhu\",\"Weiqiang Wang\",\"Liqing Zhang\",\"Jianfu Zhang\"]","published":"2025-10-05T14:29:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}