# Grand Challenge On Detecting Cheapfakes

arXiv: https://arxiv.org/abs/2304.01328 · HTML: https://mlsanity.com/paper/2304.01328/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 15 references that are in the map.
- First posted on arXiv 3 Apr 2023.

## Builds on (most cited first, 6 of 6)

- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [Fighting Fake News: Image Splice Detection via Learned Self-Consistency](https://mlsanity.com/paper/1805.04096/) (2018)
- [NewsCLIPpings: Automatic Generation of Out-of-Context Multimodal Media](https://mlsanity.com/paper/2104.05893/) (2021)
- [Detecting Photoshopped Faces by Scripting Photoshop](https://mlsanity.com/paper/1906.05856/) (2019)
- [COSMOS: Catching Out-of-Context Misinformation with Self-Supervised Learning](https://mlsanity.com/paper/2101.06278/) (2021)
- [MMSys'21 Grand Challenge on Detecting Cheapfakes](https://mlsanity.com/paper/2107.05297/) (2021)

## Built on by (most cited first, 1 of 1)

- [Cheap-fake Detection with LLM using Prompt Engineering](https://mlsanity.com/paper/2306.02776/) (2023)

## Abstract (arXiv)

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.