On the Effectiveness of Image Manipulation Detection in the Age of Social Media

TL;DR

This paper evaluates current image manipulation detection methods, analyzes their limitations, and introduces a novel deep learning pre-processing technique with an open-source toolkit to improve detection accuracy and robustness.

Contribution

It presents a comprehensive analysis of existing methods, proposes a new anomaly enhancement loss, and releases an open-source toolkit for manipulation detection.

Findings

Deep learning methods outperform learning-free approaches on benchmark datasets.

The proposed anomaly enhancement loss improves detection accuracy with minimal false positives.

The open-source toolkit facilitates standardized evaluation and comparison of manipulation detection algorithms.

Abstract

Image manipulation detection algorithms designed to identify local anomalies often rely on the manipulated regions being ``sufficiently'' different from the rest of the non-tampered regions in the image. However, such anomalies might not be easily identifiable in high-quality manipulations, and their use is often based on the assumption that certain image phenomena are associated with the use of specific editing tools. This makes the task of manipulation detection hard in and of itself, with state-of-the-art detectors only being able to detect a limited number of manipulation types. More importantly, in cases where the anomaly assumption does not hold, the detection of false positives in otherwise non-manipulated images becomes a serious problem. To understand the current state of manipulation detection, we present an in-depth analysis of deep learning-based and learning-free methods, assessing their performance on different benchmark datasets containing tampered and non-tampered samples. We provide a comprehensive study of their suitability for detecting different manipulations as well as their robustness when presented with non-tampered data. Furthermore, we propose a novel deep learning-based pre-processing technique that accentuates the anomalies present in manipulated regions to make them more identifiable by a variety of manipulation detection methods. To this end, we introduce an anomaly enhancement loss that, when used with a residual architecture, improves the performance of different detection algorithms with a minimal introduction of false positives on the non-manipulated data. Lastly, we introduce an open-source manipulation detection toolkit comprising a number of standard detection algorithms.