Benchmarking Scientific Image Forgery Detectors
This addresses a critical bottleneck for researchers in scientific integrity by providing accessible tools and data, though it is incremental in building on existing forgery operations.
The authors tackled the lack of available datasets for evaluating scientific image forgery detectors by creating an open-source library and benchmark with 39,423 images, and they evaluated state-of-the-art copy-move detection methods using a new metric.
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.