Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios

2025-09-11

AI Summary

Existing AI-generated image detection models lack rigorous evaluation of generalization and robustness under real-world conditions. Method: We introduce RRDataset—the first benchmark explicitly designed for realistic challenges—encompassing seven representative scenarios, multi-round social media propagation, and diverse re-digitization operations (e.g., compression, format conversion, screen recapture). We propose the first comprehensive evaluation framework jointly assessing scene generalization, internet transmission robustness, and re-digitization robustness, systematically evaluating 17 detectors and 10 vision-language models. Contribution/Results: Experiments reveal substantial performance degradation of state-of-the-art methods along authentic dissemination chains, while humans demonstrate superior adaptability under few-shot conditions. Our large-scale human-machine comparative study quantifies critical technical bottlenecks and provides empirical foundations for designing robust detection algorithms and human-AI collaborative mechanisms.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Natural Language Processing: Safety and Robustness
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image detection methods have partially addressed these concerns, a substantial research gap remains in evaluating their performance under complex real-world conditions. This paper introduces the Real-World Robustness Dataset (RRDataset) for comprehensive evaluation of detection models across three dimensions: 1) Scenario Generalization: RRDataset encompasses high-quality images from seven major scenarios (War and Conflict, Disasters and Accidents, Political and Social Events, Medical and Public Health, Culture and Religion, Labor and Production, and everyday life), addressing existing dataset gaps from a content perspective. 2) Internet Transmission Robustness: examining detector performance on images that have undergone multiple rounds of sharing across various social media platforms. 3) Re-digitization Robustness: assessing model effectiveness on images altered through four distinct re-digitization methods. We benchmarked 17 detectors and 10 vision-language models (VLMs) on RRDataset and conducted a large-scale human study involving 192 participants to investigate human few-shot learning capabilities in detecting AI-generated images. The benchmarking results reveal the limitations of current AI detection methods under real-world conditions and underscore the importance of drawing on human adaptability to develop more robust detection algorithms.

Problem

• Benchmarking AI-generated image detection in real-world scenarios
• Evaluating detector robustness under internet transmission distortions
• Assessing model performance across diverse content domains

Innovation

• Real-World Robustness Dataset for evaluation
• Testing across scenario generalization and transmission
• Benchmarking detectors and vision-language models