SWIFT: Semantic Watermarking for Image Forgery Thwarting

TL;DR

This paper introduces SWIFT, a deep-learning based semantic watermarking method that embeds image captions into images to improve tampering detection and robustness against edits, bridging traditional watermarking and forensic techniques.

Contribution

It adapts the HiDDeN architecture to embed high-dimensional semantic vectors, enhancing robustness and introducing a confidence metric for practical image integrity verification.

Findings

Significant robustness improvement on malicious and benign edits

Effective embedding and extraction of high-dimensional semantic vectors

Enhanced practical applicability with confidence metric

Abstract

This paper proposes a novel approach towards image authentication and tampering detection by using watermarking as a communication channel for semantic information. We modify the HiDDeN deep-learning watermarking architecture to embed and extract high-dimensional real vectors representing image captions. Our method improves significantly robustness on both malign and benign edits. We also introduce a local confidence metric correlated with Message Recovery Rate, enhancing the method's practical applicability. This approach bridges the gap between traditional watermarking and passive forensic methods, offering a robust solution for image integrity verification.