MIRAGE: Towards AI-Generated Image Detection in the Wild

TL;DR

This paper introduces Mirage, a new benchmark for detecting AI-generated images in real-world scenarios, and proposes Mirage-R1, a vision-language model that achieves state-of-the-art performance by combining heuristic reasoning and adaptive inference strategies.

Contribution

The paper presents Mirage, a challenging in-the-wild AIGI detection benchmark, and Mirage-R1, a novel vision-language model with reflective reasoning and adaptive inference for improved detection accuracy.

Findings

Mirage-R1 outperforms existing detectors by 5% on Mirage and 10% on public benchmarks.

The benchmark includes real-world AIGI data verified by experts and synthesized datasets simulating realistic AIGI.

Mirage-R1 balances inference speed and accuracy through adaptive thinking strategies.

Abstract

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.