Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes

TL;DR

This paper introduces GAPL, a novel framework for AI-generated image detection that overcomes data heterogeneity and model bottlenecks, achieving state-of-the-art results across various generators.

Contribution

GAPL employs generator-aware prototypes and a two-stage training scheme to enhance detection robustness and generalization in AI-generated image detection.

Findings

GAPL outperforms existing methods on multiple benchmarks.

It effectively counters data heterogeneity with structured prototypes.

Two-stage training improves discriminative power without losing pretrained knowledge.

Abstract

The pursuit of a universal AI-generated image (AIGI) detector often relies on aggregating data from numerous generators to improve generalization. However, this paper identifies a paradoxical phenomenon we term the Benefit then Conflict dilemma, where detector performance stagnates and eventually degrades as source diversity expands. Our systematic analysis, diagnoses this failure by identifying two core issues: severe data-level heterogeneity, which causes the feature distributions of real and synthetic images to increasingly overlap, and a critical model-level bottleneck from fixed, pretrained encoders that cannot adapt to the rising complexity. To address these challenges, we propose Generator-Aware Prototype Learning (GAPL), a framework that constrain representation with a structured learning paradigm. GAPL learns a compact set of canonical forgery prototypes to create a unified, low-variance feature space, effectively countering data heterogeneity.To resolve the model bottleneck, it employs a two-stage training scheme with Low-Rank Adaptation, enhancing its discriminative power while preserving valuable pretrained knowledge. This approach establishes a more robust and generalizable decision boundary. Through extensive experiments, we demonstrate that GAPL achieves state-of-the-art performance, showing superior detection accuracy across a wide variety of GAN and diffusion-based generators. Code is available at https://github.com/UltraCapture/GAPL