RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors

TL;DR

This paper introduces RAID, a large dataset of adversarial examples designed to evaluate and challenge the robustness of AI-generated image detectors, revealing their vulnerability to adversarial attacks.

Contribution

The paper presents RAID, a comprehensive dataset of adversarial images for testing the robustness of AI-generated image detectors, created through attacks on multiple detectors and image models.

Findings

State-of-the-art detectors are easily deceived by adversarial examples.

The dataset enables quick estimation of detector robustness.

Adversarial transferability is high across unseen detectors.

Abstract

AI-generated images have reached a quality level at which humans are incapable of reliably distinguishing them from real images. To counteract the inherent risk of fraud and disinformation, the detection of AI-generated images is a pressing challenge and an active research topic. While many of the presented methods claim to achieve high detection accuracy, they are usually evaluated under idealized conditions. In particular, the adversarial robustness is often neglected, potentially due to a lack of awareness or the substantial effort required to conduct a comprehensive robustness analysis. In this work, we tackle this problem by providing a simpler means to assess the robustness of AI-generated image detectors. We present RAID (Robust evaluation of AI-generated image Detectors), a dataset of 72k diverse and highly transferable adversarial examples. The dataset is created by running attacks against an ensemble of seven state-of-the-art detectors and images generated by four different text-to-image models. Extensive experiments show that our methodology generates adversarial images that transfer with a high success rate to unseen detectors, which can be used to quickly provide an approximate yet still reliable estimate of a detector's adversarial robustness. Our findings indicate that current state-of-the-art AI-generated image detectors can be easily deceived by adversarial examples, highlighting the critical need for the development of more robust methods. We release our dataset at https://huggingface.co/datasets/aimagelab/RAID and evaluation code at https://github.com/pralab/RAID.