Proactive Image Manipulation Detection

TL;DR

This paper introduces a proactive image manipulation detection method that estimates templates to improve detection accuracy across various generative models, outperforming prior passive detection techniques.

Contribution

The paper proposes a novel proactive detection scheme that estimates templates to enhance manipulation detection, demonstrating significant improvements over existing passive methods.

Findings

Outperforms prior work by 16% for CycleGAN and 32% for GauGAN.

Generalizes well to multiple GMs with a 10% average improvement.

Achieves higher accuracy by using template estimation to discriminate manipulated images.

Abstract

Image manipulation detection algorithms are often trained to discriminate between images manipulated with particular Generative Models (GMs) and genuine/real images, yet generalize poorly to images manipulated with GMs unseen in the training. Conventional detection algorithms receive an input image passively. By contrast, we propose a proactive scheme to image manipulation detection. Our key enabling technique is to estimate a set of templates which when added onto the real image would lead to more accurate manipulation detection. That is, a template protected real image, and its manipulated version, is better discriminated compared to the original real image vs. its manipulated one. These templates are estimated using certain constraints based on the desired properties of templates. For image manipulation detection, our proposed approach outperforms the prior work by an average precision of 16% for CycleGAN and 32% for GauGAN. Our approach is generalizable to a variety of GMs showing an improvement over prior work by an average precision of 10% averaged across 12 GMs. Our code is available at https://www.github.com/vishal3477/proactive_IMD.