# Embedding Trust at Scale: Physics-Aware Neural Watermarking for Secure and Verifiable Data Pipelines

arXiv: https://arxiv.org/abs/2506.12032 · HTML: https://mlsanity.com/paper/2506.12032/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 22 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 11 of 11)

- [Machine Learning for Fluid Mechanics](https://mlsanity.com/paper/1905.11075/) (2019)
- [Invisible Image Watermarks Are Provably Removable Using Generative AI](https://mlsanity.com/paper/2306.01953/) (2023)
- [WAVES: Benchmarking the Robustness of Image Watermarks](https://mlsanity.com/paper/2401.08573/) (2024)
- [Supervised GAN Watermarking for Intellectual Property Protection](https://mlsanity.com/paper/2209.03466/) (2022)
- [SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning](https://mlsanity.com/paper/2306.14070/) (2023)
- [Removing Watermarks with Partial Regeneration using Semantic Information](https://mlsanity.com/paper/2505.08234/) (2025)
- [Transforming Cyber Defense: Harnessing Agentic and Frontier AI for Proactive, Ethical Threat Intelligence](https://mlsanity.com/paper/2503.00164/) (2025)
- [Engineering Risk-Aware, Security-by-Design Frameworks for Assurance of Large-Scale Autonomous AI Models](https://mlsanity.com/paper/2505.06409/) (2025)
- [CyberSentinel: An Emergent Threat Detection System for AI Security](https://mlsanity.com/paper/2502.14966/) (2025)
- [The Cyber Immune System: Harnessing Adversarial Forces for Security Resilience](https://mlsanity.com/paper/2502.17698/) (2025)
- [Towards Conditional Generation of Minimal Action Potential Pathways for Molecular Dynamics](https://mlsanity.com/paper/2111.14053/) (2021)

## Abstract (arXiv)

We present a robust neural watermarking framework for scientific data integrity, targeting high-dimensional fields common in climate modeling and fluid simulations. Using a convolutional autoencoder, binary messages are invisibly embedded into structured data such as temperature, vorticity, and geopotential. Our method ensures watermark persistence under lossy transformations - including noise injection, cropping, and compression - while maintaining near-original fidelity (sub-1% MSE). Compared to classical singular value decomposition (SVD)-based watermarking, our approach achieves >98% bit accuracy and visually indistinguishable reconstructions across ERA5 and Navier-Stokes datasets. This system offers a scalable, model-compatible tool for data provenance, auditability, and traceability in high-performance scientific workflows, and contributes to the broader goal of securing AI systems through verifiable, physics-aware watermarking. We evaluate on physically grounded scientific datasets as a representative stress-test; the framework extends naturally to other structured domains such as satellite imagery and autonomous-vehicle perception streams.