Comprint: Image Forgery Detection and Localization using Compression Fingerprints
This addresses the challenge of identifying manipulated images in the wild for combating misinformation, representing a strong specific gain in forensic tools.
The paper tackles the problem of detecting and localizing image forgeries in real-world conditions, where unknown manipulation types and recompression damage traces, by introducing Comprint, a method based on compression fingerprints trained only on pristine data, and its fusion with Noiseprint, achieving significant outperformance over state-of-the-art methods on five evaluation datasets.
Manipulation tools that realistically edit images are widely available, making it easy for anyone to create and spread misinformation. In an attempt to fight fake news, forgery detection and localization methods were designed. However, existing methods struggle to accurately reveal manipulations found in images on the internet, i.e., in the wild. That is because the type of forgery is typically unknown, in addition to the tampering traces being damaged by recompression. This paper presents Comprint, a novel forgery detection and localization method based on the compression fingerprint or comprint. It is trained on pristine data only, providing generalization to detect different types of manipulation. Additionally, we propose a fusion of Comprint with the state-of-the-art Noiseprint, which utilizes a complementary camera model fingerprint. We carry out an extensive experimental analysis and demonstrate that Comprint has a high level of accuracy on five evaluation datasets that represent a wide range of manipulation types, mimicking in-the-wild circumstances. Most notably, the proposed fusion significantly outperforms state-of-the-art reference methods. As such, Comprint and the fusion Comprint+Noiseprint represent a promising forensics tool to analyze in-the-wild tampered images.