CVAIAug 17, 2025

MIRAGE: Towards AI-Generated Image Detection in the Wild

arXiv:2508.13223v17 citationsh-index: 5
Originality Incremental advance
AI Analysis

This addresses the threat to information security and public trust from AI-generated images, but it is incremental as it builds on existing detection methods with a new benchmark and model.

The paper tackles the problem of detecting AI-generated images in real-world scenarios, where existing detectors fail to generalize, and introduces Mirage-R1, a vision-language model that achieves state-of-the-art performance with 5% and 10% improvements on new and public benchmarks, respectively.

The spreading of AI-generated images (AIGI), driven by advances in generative AI, poses a significant threat to information security and public trust. Existing AIGI detectors, while effective against images in clean laboratory settings, fail to generalize to in-the-wild scenarios. These real-world images are noisy, varying from ``obviously fake" images to realistic ones derived from multiple generative models and further edited for quality control. We address in-the-wild AIGI detection in this paper. We introduce Mirage, a challenging benchmark designed to emulate the complexity of in-the-wild AIGI. Mirage is constructed from two sources: (1) a large corpus of Internet-sourced AIGI verified by human experts, and (2) a synthesized dataset created through the collaboration between multiple expert generators, closely simulating the realistic AIGI in the wild. Building on this benchmark, we propose Mirage-R1, a vision-language model with heuristic-to-analytic reasoning, a reflective reasoning mechanism for AIGI detection. Mirage-R1 is trained in two stages: a supervised-fine-tuning cold start, followed by a reinforcement learning stage. By further adopting an inference-time adaptive thinking strategy, Mirage-R1 is able to provide either a quick judgment or a more robust and accurate conclusion, effectively balancing inference speed and performance. Extensive experiments show that our model leads state-of-the-art detectors by 5% and 10% on Mirage and the public benchmark, respectively. The benchmark and code will be made publicly available.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes