LOTA: Bit-Planes Guided AI-Generated Image Detection

2025-10-15

AI Summary

To address the high computational cost and difficulty in modeling intrinsic noise inherent in reconstruction-error-based methods for AI-generated image detection, this paper proposes a lightweight bit-plane-based noise feature extraction approach. Our method innovatively leverages low-order bit planes to capture the native noise patterns of images, enhances discriminative artifacts via multi-directional gradient computation, and selects the most salient gradient blocks to highlight generation-specific anomalies. A lightweight classification head enables end-to-end discrimination. The proposed method achieves millisecond-level inference latency and attains a mean accuracy of 98.9% on the GenImage benchmark—substantially outperforming state-of-the-art approaches. It demonstrates strong cross-model generalization and accelerates detection speed by nearly two orders of magnitude, achieving an exceptional balance between efficiency and robustness.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The rapid advancement of GAN and Diffusion models makes it more difficult to distinguish AI-generated images from real ones. Recent studies often use image-based reconstruction errors as an important feature for determining whether an image is AI-generated. However, these approaches typically incur high computational costs and also fail to capture intrinsic noisy features present in the raw images. To solve these problems, we innovatively refine error extraction by using bit-plane-based image processing, as lower bit planes indeed represent noise patterns in images. We introduce an effective bit-planes guided noisy image generation and exploit various image normalization strategies, including scaling and thresholding. Then, to amplify the noise signal for easier AI-generated image detection, we design a maximum gradient patch selection that applies multi-directional gradients to compute the noise score and selects the region with the highest score. Finally, we propose a lightweight and effective classification head and explore two different structures: noise-based classifier and noise-guided classifier. Extensive experiments on the GenImage benchmark demonstrate the outstanding performance of our method, which achieves an average accuracy of extbf{98.9%} ( extbf{11.9}%~$uparrow$) and shows excellent cross-generator generalization capability. Particularly, our method achieves an accuracy of over 98.2% from GAN to Diffusion and over 99.2% from Diffusion to GAN. Moreover, it performs error extraction at the millisecond level, nearly a hundred times faster than existing methods. The code is at https://github.com/hongsong-wang/LOTA.

Problem

• Detecting AI-generated images using bit-plane noise patterns
• Reducing computational costs in image reconstruction error analysis
• Improving cross-generator generalization for detection models

Innovation

• Bit-plane processing extracts noise patterns
• Maximum gradient patch amplifies noise signals
• Lightweight classification head enables fast detection