Deepfake Detection Generalization with Diffusion Noise

TL;DR

This paper introduces an Attention-guided Noise Learning framework that leverages diffusion model noise to improve deepfake detection generalization, especially against diffusion-generated forgeries.

Contribution

It proposes a novel diffusion noise-based regularization method with attention guidance, enhancing detector robustness to unseen deepfake techniques.

Findings

Outperforms existing methods on multiple deepfake detection benchmarks.

Achieves state-of-the-art accuracy in detecting diffusion-generated deepfakes.

Significantly improves generalization performance without extra inference overhead.

Abstract

Deepfake detectors face growing challenges in generalization as new image synthesis techniques emerge. In particular, deepfakes generated by diffusion models are highly photorealistic and often evade detectors trained on GAN-based forgeries. This paper addresses the generalization problem in deepfake detection by leveraging diffusion noise characteristics. We propose an Attention-guided Noise Learning (ANL) framework that integrates a pre-trained diffusion model into the deepfake detection pipeline to guide the learning of more robust features. Specifically, our method uses the diffusion model's denoising process to expose subtle artifacts: the detector is trained to predict the noise contained in an input image at a given diffusion step, forcing it to capture discrepancies between real and synthetic images, while an attention-guided mechanism derived from the predicted noise is introduced to encourage the model to focus on globally distributed discrepancies rather than local patterns. By harnessing the frozen diffusion model's learned distribution of natural images, the ANL method acts as a form of regularization, improving the detector's generalization to unseen forgery types. Extensive experiments demonstrate that ANL significantly outperforms existing methods on multiple benchmarks, achieving state-of-the-art accuracy in detecting diffusion-generated deepfakes. Notably, the proposed framework boosts generalization performance (e.g., improving ACC/AP by a substantial margin on unseen models) without introducing additional overhead during inference. Our results highlight that diffusion noise provides a powerful signal for generalizable deepfake detection.