# Beyond AI-Generated Labels: Watermarking, Co-Creation, and Conflation of AI-Generation with Disinformation

arXiv: https://arxiv.org/abs/2607.13082 · HTML: https://mlsanity.com/paper/2607.13082/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 13 of its 44 references that are in the map.
- First posted on arXiv 13 Jul 2026.

## 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, 13 of 13)

- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks](https://mlsanity.com/paper/2310.00076/) (2023)
- [AI model GPT-3 (dis)informs us better than humans](https://mlsanity.com/paper/2301.11924/) (2023)
- [Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy](https://mlsanity.com/paper/2307.13808/) (2023)
- [Provably Robust Multi-bit Watermarking for AI-generated Text](https://mlsanity.com/paper/2401.16820/) (2024)
- [SynthID-Image: Image watermarking at internet scale](https://mlsanity.com/paper/2510.09263/) (2025)
- [Revisiting the Robustness of Watermarking to Paraphrasing Attacks](https://mlsanity.com/paper/2411.05277/) (2024)
- [InvisMark: Invisible and Robust Watermarking for AI-generated Image Provenance](https://mlsanity.com/paper/2411.07795/) (2024)
- [Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks](https://mlsanity.com/paper/2505.05190/) (2025)
- [Warfare:Breaking the Watermark Protection of AI-Generated Content](https://mlsanity.com/paper/2310.07726/) (2023)
- [WMCopier: Forging Invisible Image Watermarks on Arbitrary Images](https://mlsanity.com/paper/2503.22330/) (2025)
- [Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking](https://mlsanity.com/paper/2505.06827/) (2025)
- [Diffusion-Based Image Editing: An Unforeseen Adversary to Robust Invisible Watermarks](https://mlsanity.com/paper/2511.05598/) (2025)

## Abstract (arXiv)

Watermarking is often presented as a straightforward solution for distinguishing AI-generated from human-generated content, enabling platforms and regulators to trace synthetic content and detect AI-generated outputs at scale. This paper examines whether such mechanisms meaningfully address the epistemic and ethical challenges that arise in domains where the central concern is not the automation of content production, but the accuracy, intent, and deceptive potential of messages. We argue that extending watermark-based approaches to these settings is conceptually and practically misguided. Invisible watermarking encodes only model origin; when operationalized into visible AI-generated labels, it reduces complex creative processes to a misleading binary and provides no information about truthfulness. Such labels may stigmatize legitimate uses of generative tools while encouraging misplaced trust in unmarked content. Here we propose an alternative approach centered on process transparency and information literacy. We argue that these measures address the epistemic and ethical dimensions of AI-generated disinformation more effectively than visible watermark labels, reframing authorship as a transparent human practice rather than a binary indicator of machine involvement.