Detecting Generated Images by Real Images Only

TL;DR

This paper introduces a novel approach for detecting generated images by modeling only real images, enabling efficient, robust detection across various generative models with minimal training data.

Contribution

The method uniquely focuses on real images to identify a common feature subspace, improving detection efficiency and generalization without relying on generated images during training.

Findings

Achieves high detection accuracy with only real images and minimal training data.

Demonstrates robustness against post-processing techniques.

Performs well on emerging generative models.

Abstract

As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect visual artifacts in generated images or learn discriminative features from both real and generated images by massive training. This learning paradigm will result in efficiency and generalization issues, making detection methods always lag behind generation methods. This paper approaches the generated image detection problem from a new perspective: Start from real images. By finding the commonality of real images and mapping them to a dense subspace in feature space, the goal is that generated images, regardless of their generative model, are then projected outside the subspace. As a result, images from different generative models can be detected, solving some long-existing problems in the field. Experimental results show that although our method was trained only by real images and uses 99.9\% less training data than other deep learning-based methods, it can compete with state-of-the-art methods and shows excellent performance in detecting emerging generative models with high inference efficiency. Moreover, the proposed method shows robustness against various post-processing. These advantages allow the method to be used in real-world scenarios.