Grand Challenge On Detecting Cheapfakes

View on arXiv ← Back to list

Authors: Duc-Tien Dang-Nguyen, Sohail Ahmed Khan, Cise Midoglu, Michael Riegler, Pål Halvorsen, Minh-Son Dao

Published: 2023-04-03 19:50:26+00:00

AI Summary

This research paper describes a grand challenge focused on detecting out-of-context (OOC) misuse of images in news items, a type of cheapfake manipulation. The challenge uses the COSMOS dataset and aims to benchmark models capable of identifying conflicting image-caption triplets indicating miscontextualization.

Abstract

Cheapfake is a recently coined term that encompasses non-AI (cheap) manipulations of multimedia content. Cheapfakes are known to be more prevalent than deepfakes. Cheapfake media can be created using editing software for image/video manipulations, or even without using any software, by simply altering the context of an image/video by sharing the media alongside misleading claims. This alteration of context is referred to as out-of-context (OOC) misuse of media. OOC media is much harder to detect than fake media, since the images and videos are not tampered. In this challenge, we focus on detecting OOC images, and more specifically the misuse of real photographs with conflicting image captions in news items. The aim of this challenge is to develop and benchmark models that can be used to detect whether given samples (news image and associated captions) are OOC, based on the recently compiled COSMOS dataset.

Key findings

UNKNOWN (The paper outlines a challenge; results are not presented.)

Approach

The challenge focuses on developing models that can detect conflicting image-caption triplets or fake captions. Participants are tasked with creating models that predict whether image-caption pairs or triplets are out-of-context based on semantic differences or inconsistencies.

Datasets

COSMOS dataset (augmented version)

Model(s)

UNKNOWN (The paper describes a challenge, not a specific model)

Author countries

Norway, Japan

← Previous