Synthetic Image Detection: Highlights from the IEEE Video and Image Processing Cup 2022 Student Competition

TL;DR

This paper discusses the development of systems to detect AI-generated images, highlighting approaches from the 2022 IEEE VIP Cup competition aimed at combating disinformation caused by realistic synthetic media.

Contribution

It presents novel methods developed by students for distinguishing pristine images from AI-generated ones, addressing the challenge of synthetic media detection amidst advances in image synthesis technology.

Findings

Effective detection techniques demonstrated in the competition.

Identification of key features for synthetic image classification.

Improved robustness of detection methods against sophisticated generation models.

Abstract

The Video and Image Processing (VIP) Cup is a student competition that takes place each year at the IEEE International Conference on Image Processing. The 2022 IEEE VIP Cup asked undergraduate students to develop a system capable of distinguishing pristine images from generated ones. The interest in this topic stems from the incredible advances in the AI-based generation of visual data, with tools that allows the synthesis of highly realistic images and videos. While this opens up a large number of new opportunities, it also undermines the trustworthiness of media content and fosters the spread of disinformation on the internet. Recently there was strong concern about the generation of extremely realistic images by means of editing software that includes the recent technology on diffusion models. In this context, there is a need to develop robust and automatic tools for synthetic image detection.