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

2025-12-14

AI Summary

AI-generated image (AIGI) detectors face a “post-gain conflict” dilemma when confronted with increasingly diverse generative models: initial performance gains are followed by significant degradation due to escalating data heterogeneity and the rigidity of pretrained encoders, leading to feature confusion. Method: This work first identifies the synergistic degradation mechanism arising from distributional overlap across generators and insufficient model adaptability. We propose Generator-Aware Prototype Learning (GAPL), which constructs a low-variance, unified feature space via generator-aware prototype representations and alleviates encoder bottlenecks through a two-stage LoRA fine-tuning paradigm. GAPL further integrates structured contrastive learning with joint modeling of multi-source synthetic data. Contribution/Results: GAPL achieves state-of-the-art performance on both GAN- and diffusion-based AIGI detection, demonstrating superior cross-generator generalization, accuracy, 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: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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

Problem

• Detects AI-generated images across diverse generators
• Addresses performance degradation from increasing data heterogeneity
• Overcomes fixed encoder limitations with adaptive training

Innovation

• Generator-Aware Prototype Learning framework
• Low-Rank Adaptation for model enhancement
• Canonical forgery prototypes for unified features