MiRAGeNews: Multimodal Realistic AI-Generated News Detection

TL;DR

This paper introduces MiRAGeNews, a challenging dataset of real and AI-generated news images and captions, and presents a multi-modal detector that significantly outperforms existing methods in identifying AI-generated fake news content.

Contribution

The paper provides a new large-scale dataset for detecting AI-generated fake news and develops a multi-modal detector that improves accuracy over existing baselines.

Findings

Humans achieve 60% F-1 in detection.

State-of-the-art models achieve less than 24% F-1.

The proposed detector improves F-1 by +5.1% over baselines.

Abstract

The proliferation of inflammatory or misleading "fake" news content has become increasingly common in recent years. Simultaneously, it has become easier than ever to use AI tools to generate photorealistic images depicting any scene imaginable. Combining these two -- AI-generated fake news content -- is particularly potent and dangerous. To combat the spread of AI-generated fake news, we propose the MiRAGeNews Dataset, a dataset of 12,500 high-quality real and AI-generated image-caption pairs from state-of-the-art generators. We find that our dataset poses a significant challenge to humans (60% F-1) and state-of-the-art multi-modal LLMs (< 24% F-1). Using our dataset we train a multi-modal detector (MiRAGe) that improves by +5.1% F-1 over state-of-the-art baselines on image-caption pairs from out-of-domain image generators and news publishers. We release our code and data to aid future work on detecting AI-generated content.