Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection

TL;DR

This paper introduces MAFL, an adversarial feature learning framework that reduces bias in AI-generated image detection, improving cross-model generalization and performance with limited training data.

Contribution

The proposed MAFL framework effectively suppresses pattern and content biases, enhancing detection accuracy and generalization across different generative models.

Findings

Outperforms state-of-the-art methods by 10.89% in accuracy.

Achieves over 80% detection accuracy with only 320 training images.

Effectively captures shared generative features across models.

Abstract

In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality fake images, posing a serious challenge to information authenticity and credibility. Existing generated image detection methods typically enhance generalization through model architecture or network design. However, their generalization performance remains susceptible to data bias, as the training data may drive models to fit specific generative patterns and content rather than the common features shared by images from different generative models (asymmetric bias learning). To address this issue, we propose a Multi-dimensional Adversarial Feature Learning (MAFL) framework. The framework adopts a pretrained multimodal image encoder as the feature extraction backbone, constructs a real-fake feature learning network, and designs an adversarial bias-learning branch equipped with a multi-dimensional adversarial loss, forming an adversarial training mechanism between authenticity-discriminative feature learning and bias feature learning. By suppressing generation-pattern and content biases, MAFL guides the model to focus on the generative features shared across different generative models, thereby effectively capturing the fundamental differences between real and generated images, enhancing cross-model generalization, and substantially reducing the reliance on large-scale training data. Through extensive experimental validation, our method outperforms existing state-of-the-art approaches by 10.89% in accuracy and 8.57% in Average Precision (AP). Notably, even when trained with only 320 images, it can still achieve over 80% detection accuracy on public datasets.