Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement

TL;DR

This paper introduces an Uncertainty-guided Refinement Network (URN) for detecting image splicing traces in scientific publications, addressing challenges posed by disruptive factors and limited datasets, and demonstrating superior robustness and generalization.

Contribution

The paper proposes a novel URN model that suppresses unreliable information propagation and focuses on uncertain regions, along with a new diverse dataset SciSp for improved splicing detection.

Findings

URN outperforms existing methods on benchmark datasets.

URN demonstrates robustness against post-processing techniques.

The SciSp dataset is the largest and most diverse for scientific image splicing detection.

Abstract

Recently, a surge in scientific publications suspected of image manipulation has led to numerous retractions, bringing the issue of image integrity into sharp focus. Although research on forensic detectors for image plagiarism and image synthesis exists, the detection of image splicing traces in scientific publications remains unexplored. Compared to image duplication and synthesis, image splicing detection is more challenging due to the lack of reference images and the typically small tampered areas. Furthermore, disruptive factors in scientific images, such as artifacts from digital compression, abnormal patterns, and noise from physical operations, present misleading features like splicing traces, significantly increasing the difficulty of this task. Moreover, the scarcity of high-quality datasets of spliced scientific images limits potential advancements. In this work, we propose an Uncertainty-guided Refinement Network (URN) to mitigate the impact of these disruptive factors. Our URN can explicitly suppress the propagation of unreliable information flow caused by disruptive factors between regions, thus obtaining robust splicing features. Additionally, the URN is designed to concentrate improvements in uncertain prediction areas during the decoding phase. We also construct a dataset for image splicing detection (SciSp) containing 1,290 spliced images. Compared to existing datasets, SciSp includes the largest number of spliced images and the most diverse sources. Comprehensive experiments conducted on three benchmark datasets demonstrate the superiority of our approach. We also validate the URN's generalisability in resisting cross-dataset domain shifts and its robustness against various post-processing techniques, including advanced deep-learning-based inpainting.