We present DualSecure, a resolution-agnostic semi-fragile watermarking framework that combines semantic tamper detection with provenance attribution. The proposed method embeds an imperceptible watermark that remains robust to benign transformations while degrading under semantic image alterations, enabling reliable detection, localization, and interpretation of manipulations. In addition to verifying integrity, the presented solution can identify the likely source of an image, such as a specific social media or communication platform, based on characteristic alterations introduced during its processing pipeline. The system maintains high visual transparency and is scalable to very high-resolution images, including HD, Full HD, and 2K. Experimental evaluation demonstrates strong performance in both manipulation detection and source attribution across a diverse set of image resolutions and processing conditions.
Duszejko et al. (Wed,) studied this question.