The PS-Battles Dataset - an Image Collection for Image Manipulation Detection

TL;DR

This paper introduces the PS-Battles dataset, a large collection of original and manipulated images, aimed at advancing research in detecting digital media tampering and derivations.

Contribution

The paper presents a new, extensive dataset for image manipulation detection, facilitating the development of more reliable tampering detection methods.

Findings

Dataset contains 102,028 images and 11,142 subsets.

Provides a diverse set of manipulated derivatives for each original image.

Supports research in media derivation and tampering detection.

Abstract

The boost of available digital media has led to a significant increase in derivative work. With tools for manipulating objects becoming more and more mature, it can be very difficult to determine whether one piece of media was derived from another one or tampered with. As derivations can be done with malicious intent, there is an urgent need for reliable and easily usable tampering detection methods. However, even media considered semantically untampered by humans might have already undergone compression steps or light post-processing, making automated detection of tampering susceptible to false positives. In this paper, we present the PS-Battles dataset which is gathered from a large community of image manipulation enthusiasts and provides a basis for media derivation and manipulation detection in the visual domain. The dataset consists of 102'028 images grouped into 11'142 subsets, each containing the original image as well as a varying number of manipulated derivatives.