Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources

TL;DR

This paper introduces a novel multi-modal fact-checking method that automates verification of image-caption pairs against web evidence, significantly improving accuracy in detecting out-of-context misinformation.

Contribution

It proposes a new architecture, the Consistency-Checking Network, and a multi-modal cycle-consistency check, pioneering open-domain, content-based multi-modal fact-checking with a new benchmark.

Findings

Outperforms previous baselines in accuracy

First benchmark for open-domain multi-modal fact-checking

Effective integration of textual and visual evidence

Abstract

Misinformation is now a major problem due to its potential high risks to our core democratic and societal values and orders. Out-of-context misinformation is one of the easiest and effective ways used by adversaries to spread viral false stories. In this threat, a real image is re-purposed to support other narratives by misrepresenting its context and/or elements. The internet is being used as the go-to way to verify information using different sources and modalities. Our goal is an inspectable method that automates this time-consuming and reasoning-intensive process by fact-checking the image-caption pairing using Web evidence. To integrate evidence and cues from both modalities, we introduce the concept of 'multi-modal cycle-consistency check'; starting from the image/caption, we gather textual/visual evidence, which will be compared against the other paired caption/image, respectively. Moreover, we propose a novel architecture, Consistency-Checking Network (CCN), that mimics the layered human reasoning across the same and different modalities: the caption vs. textual evidence, the image vs. visual evidence, and the image vs. caption. Our work offers the first step and benchmark for open-domain, content-based, multi-modal fact-checking, and significantly outperforms previous baselines that did not leverage external evidence.