Detecting Out-of-Context Image-Caption Pairs in News: A Counter-Intuitive Method

TL;DR

This paper introduces a novel method leveraging generative image models to detect out-of-context image-caption pairs in news, supported by new datasets and analysis of generative model performance.

Contribution

The paper presents two new datasets of generated images and a novel detection approach for out-of-context media in news articles.

Findings

Effective detection of out-of-context image-caption pairs.

Generative models like DALL-E 2 and Stable-Diffusion can be analyzed for fake news detection.

New datasets facilitate future research in cheapfake detection.

Abstract

The growth of misinformation and re-contextualized media in social media and news leads to an increasing need for fact-checking methods. Concurrently, the advancement in generative models makes cheapfakes and deepfakes both easier to make and harder to detect. In this paper, we present a novel approach using generative image models to our advantage for detecting Out-of-Context (OOC) use of images-caption pairs in news. We present two new datasets with a total of $6800$ images generated using two different generative models including (1) DALL-E 2, and (2) Stable-Diffusion. We are confident that the method proposed in this paper can further research on generative models in the field of cheapfake detection, and that the resulting datasets can be used to train and evaluate new models aimed at detecting cheapfakes. We run a preliminary qualitative and quantitative analysis to evaluate the performance of each image generation model for this task, and evaluate a handful of methods for computing image similarity.