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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Tallam, Krti
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912429733052416
author Tallam, Krti
author_facet Tallam, Krti
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Embedding Trust at Scale: Physics-Aware Neural Watermarking for Secure and Verifiable Data Pipelines
Tallam, Krti
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Cryptography and Security
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.
title Embedding Trust at Scale: Physics-Aware Neural Watermarking for Secure and Verifiable Data Pipelines
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Cryptography and Security
url https://arxiv.org/abs/2506.12032