IConMark: Robust Interpretable Concept-Based Watermark For AI Images

TL;DR

IConMark introduces a semantic, interpretable watermarking method for AI-generated images that is robust against adversarial attacks and augmentations, enhancing digital authenticity verification.

Contribution

The paper presents IConMark, a novel semantic watermarking technique that embeds interpretable concepts into AI images, improving robustness and human interpretability over traditional methods.

Findings

IConMark outperforms baselines in watermark detection accuracy.

Hybrid approaches further improve robustness against manipulations.

Watermarks remain human-readable and verifiable.

Abstract

With the rapid rise of generative AI and synthetic media, distinguishing AI-generated images from real ones has become crucial in safeguarding against misinformation and ensuring digital authenticity. Traditional watermarking techniques have shown vulnerabilities to adversarial attacks, undermining their effectiveness in the presence of attackers. We propose IConMark, a novel in-generation robust semantic watermarking method that embeds interpretable concepts into AI-generated images, as a first step toward interpretable watermarking. Unlike traditional methods, which rely on adding noise or perturbations to AI-generated images, IConMark incorporates meaningful semantic attributes, making it interpretable to humans and hence, resilient to adversarial manipulation. This method is not only robust against various image augmentations but also human-readable, enabling manual verification of watermarks. We demonstrate a detailed evaluation of IConMark's effectiveness, demonstrating its superiority in terms of detection accuracy and maintaining image quality. Moreover, IConMark can be combined with existing watermarking techniques to further enhance and complement its robustness. We introduce IConMark+SS and IConMark+TM, hybrid approaches combining IConMark with StegaStamp and TrustMark, respectively, to further bolster robustness against multiple types of image manipulations. Our base watermarking technique (IConMark) and its variants (+TM and +SS) achieve 10.8%, 14.5%, and 15.9% higher mean area under the receiver operating characteristic curve (AUROC) scores for watermark detection, respectively, compared to the best baseline on various datasets.