Beyond Known Fakes: Generalized Detection of AI-Generated Images via Post-hoc Distribution Alignment

TL;DR

This paper introduces Post-hoc Distribution Alignment (PDA), a model-agnostic framework that detects AI-generated images by comparing distribution alignment of regenerated images, enabling effective detection of unknown fake images without retraining.

Contribution

The paper presents PDA, a novel distribution alignment approach that generalizes AI-generated image detection to unknown models without retraining or model-specific artifacts.

Findings

Achieves 96.69% average detection accuracy across 16 models.

Outperforms baseline methods by 10.71%.

Demonstrates robustness to distribution shifts and transformations.

Abstract

The rapid proliferation of highly realistic AI-generated images poses serious security threats such as misinformation and identity fraud. Detecting generated images in open-world settings is particularly challenging when they originate from unknown generators, as existing methods typically rely on model-specific artifacts and require retraining on new fake data, limiting their generalization and scalability. In this work, we propose Post-hoc Distribution Alignment (PDA), a generalized and model-agnostic framework for detecting AI-generated images under unknown generative threats. Specifically, PDA reformulates detection as a distribution alignment task by regenerating test images through a known generative model. When real images are regenerated, they inherit model-specific artifacts and align with the known fake distribution. In contrast, regenerated unknown fakes contain incompatible or mixed artifacts and remain misaligned. This difference allows an existing detector, trained on the known generative model, to accurately distinguish real images from unknown fakes without requiring access to unseen data or retraining. Extensive experiments across 16 state-of-the-art generative models, including GANs, diffusion models, and commercial text-to-image APIs (e.g., Midjourney), demonstrate that PDA achieves average detection accuracy of 96.69%, outperforming the best baseline by 10.71%. Comprehensive ablation studies and robustness analyses further confirm PDA's generalizability and resilience to distribution shifts and image transformations. Overall, our work provides a practical and scalable solution for real-world AI-generated image detection where new generative models emerge continuously.