Fighting Fake News: Image Splice Detection via Learned Self-Consistency

TL;DR

This paper introduces a novel image manipulation detection method that leverages EXIF metadata for training on real images, achieving state-of-the-art results in identifying and localizing splices without using manipulated training data.

Contribution

The paper presents a self-consistency based learning algorithm trained solely on real images and EXIF data, enabling effective detection of image splices without manipulated examples.

Findings

Achieves state-of-the-art performance on image forensics benchmarks.

Does not require manipulated images for training.

Effectively localizes image splices.

Abstract

Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient amounts of manipulated training data. In this paper, we propose a learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs. The algorithm uses the automatically recorded photo EXIF metadata as supervisory signal for training a model to determine whether an image is self-consistent -- that is, whether its content could have been produced by a single imaging pipeline. We apply this self-consistency model to the task of detecting and localizing image splices. The proposed method obtains state-of-the-art performance on several image forensics benchmarks, despite never seeing any manipulated images at training. That said, it is merely a step in the long quest for a truly general purpose visual forensics tool.