ACM Multimedia Grand Challenge on Detecting Cheapfakes

View on arXiv ← Back to list

Authors: Shivangi Aneja, Cise Midoglu, Duc-Tien Dang-Nguyen, Sohail Ahmed Khan, Michael Riegler, Pål Halvorsen, Chris Bregler, Balu Adsumilli

Published: 2022-07-29 08:02:42+00:00

AI Summary

This research paper presents an ACM Multimedia Grand Challenge focused on detecting out-of-context (OOC) image misuse in news items, a type of cheapfake. The challenge uses the COSMOS dataset to benchmark models' ability to identify conflicting image-caption pairs 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 describes a challenge, not the results of specific models. Results would be from participants' submissions). The challenge aims to motivate research and benchmark models for detecting OOC image misuse, a relatively unexplored area in the field of misinformation detection.

Approach

The challenge focuses on developing models that can detect conflicting image-caption triplets or fake captions. Participants are evaluated on both the effectiveness of their models in correctly classifying OOC and NOOC instances and the efficiency (latency, parameters, size) of their solutions.

Datasets

COSMOS dataset (a subset used for the challenge)

Model(s)

UNKNOWN (the challenge is to develop and benchmark models; no specific model is proposed in the description)

Author countries

Germany, Norway, United States

← Previous