# IConMark: Robust Interpretable Concept-Based Watermark For AI Images

arXiv: https://arxiv.org/abs/2507.13407 · HTML: https://mlsanity.com/paper/2507.13407/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 18 of its 26 references that are in the map.
- First posted on arXiv 17 Jul 2025.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust](https://mlsanity.com/paper/2305.20030/) (2023)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [WAVES: Benchmarking the Robustness of Image Watermarks](https://mlsanity.com/paper/2401.08573/) (2024)
- [Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks](https://mlsanity.com/paper/2310.00076/) (2023)
- [An Undetectable Watermark for Generative Image Models](https://mlsanity.com/paper/2410.07369/) (2024)
- [Watermark Anything with Localized Messages](https://mlsanity.com/paper/2411.07231/) (2024)
- [TrustMark: Universal Watermarking for Arbitrary Resolution Images](https://mlsanity.com/paper/2311.18297/) (2023)
- [Consistency-diversity-realism Pareto fronts of conditional image generative models](https://mlsanity.com/paper/2406.10429/) (2024)
- [Securing the Future of GenAI: Policy and Technology](https://mlsanity.com/paper/2407.12999/) (2024)
- [DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking](https://mlsanity.com/paper/2406.02836/) (2024)

## Built on by (most cited first, 3 of 3)

- [First-Place Solution to NeurIPS 2024 Invisible Watermark Removal Challenge](https://mlsanity.com/paper/2508.21072/) (2025)
- [Where is the Watermark? Interpretable Watermark Detection at the Block Level](https://mlsanity.com/paper/2512.14994/) (2025)
- [UniMark: Unified Adaptive Multi-bit Watermarking for Autoregressive Image Generators](https://mlsanity.com/paper/2604.11843/) (2026)

## Abstract (arXiv)

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.