PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection

TL;DR

This paper introduces PatchCraft, a novel method for detecting AI-generated images by analyzing texture patches, which remains effective across various generative models and outperforms existing detectors.

Contribution

The paper proposes a texture patch-based detection method with Smash&Reconstruction preprocessing and inter-pixel correlation analysis, along with a comprehensive benchmark for evaluation.

Findings

Outperforms state-of-the-art detectors significantly

Effective across 17 different generative models

Provides a new benchmark and leaderboard for AI-generated image detection

Abstract

Recent generative models show impressive performance in generating photographic images. Humans can hardly distinguish such incredibly realistic-looking AI-generated images from real ones. AI-generated images may lead to ubiquitous disinformation dissemination. Therefore, it is of utmost urgency to develop a detector to identify AI generated images. Most existing detectors suffer from sharp performance drops over unseen generative models. In this paper, we propose a novel AI-generated image detector capable of identifying fake images created by a wide range of generative models. We observe that the texture patches of images tend to reveal more traces left by generative models compared to the global semantic information of the images. A novel Smash&Reconstruction preprocessing is proposed to erase the global semantic information and enhance texture patches. Furthermore, pixels in rich texture regions exhibit more significant fluctuations than those in poor texture regions. Synthesizing realistic rich texture regions proves to be more challenging for existing generative models. Based on this principle, we leverage the inter-pixel correlation contrast between rich and poor texture regions within an image to further boost the detection performance. In addition, we build a comprehensive AI-generated image detection benchmark, which includes 17 kinds of prevalent generative models, to evaluate the effectiveness of existing baselines and our approach. Our benchmark provides a leaderboard for follow-up studies. Extensive experimental results show that our approach outperforms state-of-the-art baselines by a significant margin. Our project: https://fdmas.github.io/AIGCDetect