RAID: Towards Robust AI-Generated Image Detection with Bit Reversed Images

ICLR 2026 Conference Submission14784 Authors

Keywords: AI-Generated Image Detection, Bit-Plane-Based Image Processing

TL;DR: We innovatively tackle AI-generated image detection based on bit-planes and present a simple yet effective pipeline based on bit reversed image.

Abstract: The rapid advancement of image generation models has made it increasingly difficult for people to distinguish AI-generated images from real ones. To prevent the potential risks associated with the misuse of fake images, AI-generated image detection has gained significant attention. Existing methods neglect the inherent differences between real and fake images, thus lacking robustness and generalization ability. In this work, we innovatively investigate AI-generated image detection using bit-planes, and introduce the bit reversed image. We propose a simple yet effective pipeline consisting of construction of bit reversed images, gradient-based patch selection and a convolutional classifier. Extensive experiments on more than 32 benchmarks verify the effectiveness of our approach across different settings, including evaluations of generalization capability and zero-shot performance. Particularly, our approach achieves nearly 100% accuracy on eight benchmarks for cross-generator evaluation on the GenImage dataset.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 14784