Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection

TL;DR

This paper introduces Stay Positive, an algorithm that enhances fake image detection by focusing solely on generative artifacts, thereby reducing false positives caused by spurious patterns and improving robustness.

Contribution

The paper proposes a novel method to train detectors that ignore real image artifacts, improving generalization and robustness in AI-generated image detection.

Findings

Detectors trained with Stay Positive are less affected by spurious correlations.

The method improves detection of inpainted real images.

Enhanced robustness to post-processing effects.

Abstract

Detecting AI generated images is a challenging yet essential task. A primary difficulty arises from the detectors tendency to rely on spurious patterns, such as compression artifacts, which can influence its decisions. These issues often stem from specific patterns that the detector associates with the real data distribution, making it difficult to isolate the actual generative traces. We argue that an image should be classified as fake if and only if it contains artifacts introduced by the generative model. Based on this premise, we propose Stay Positive, an algorithm designed to constrain the detectors focus to generative artifacts while disregarding those associated with real data. Experimental results demonstrate that detectors trained with Stay Positive exhibit reduced susceptibility to spurious correlations, leading to improved generalization and robustness to post processing. Additionally, unlike detectors that associate artifacts with real images, those that focus purely on fake artifacts are better at detecting inpainted real images.