Benchmarking Scientific Image Forgery Detectors

TL;DR

This paper introduces an open-source library and a large benchmark dataset for scientific image forgery detection, addressing data scarcity and legal issues in the field, and evaluates current detection methods using this new resource.

Contribution

It provides the first extensive, realistic scientific image forgery dataset and an open-source toolkit for generating such forgeries, facilitating research and evaluation.

Findings

State-of-the-art copy-move detection methods are evaluated on the new dataset.

The dataset contains 39,423 images with detailed ground-truth annotations.

A new metric for consistent match detection is proposed and tested.

Abstract

The scientific image integrity area presents a challenging research bottleneck, the lack of available datasets to design and evaluate forensic techniques. Its data sensitivity creates a legal hurdle that prevents one to rely on real tampered cases to build any sort of accessible forensic benchmark. To mitigate this bottleneck, we present an extendable open-source library that reproduces the most common image forgery operations reported by the research integrity community: duplication, retouching, and cleaning. Using this library and realistic scientific images, we create a large scientific forgery image benchmark (39,423 images) with an enriched ground-truth. In addition, concerned about the high number of retracted papers due to image duplication, this work evaluates the state-of-the-art copy-move detection methods in the proposed dataset, using a new metric that asserts consistent match detection between the source and the copied region. The dataset and source-code will be freely available upon acceptance of the paper.