SWIFT: Semantic Watermarking for Image Forgery Thwarting
This provides a robust solution for image integrity verification, bridging traditional watermarking and passive forensic methods.
The paper tackles image authentication and tampering detection by embedding semantic information (image captions) as watermarks using a modified HiDDeN architecture, resulting in significantly improved robustness against both malign and benign edits.
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.