Floragasse 7 – 5th floor, 1040 Vienna

News

New paper in IEEE Transactions on Information Forensics and Security

A new paper, “NCorr-FP: A Neighbourhood-Based Correlation-Preserving Fingerprinting Scheme for Intellectual Property Protection of Structured Data,” led by first author Tanja Šarčević, researcher at CDL Astra, and co-authored by Andreas Rauber, key researcher at SBA Research and Associate Professor at TU Wien, and Rudolf Mayer, senior researcher at SBA Research and lead of the Machine Learning and Data Management Research Group, was published in IEEE Transactions on Information Forensics and Security Vol 21.

half body portrait of man © Niklas Schnaubelt

Abstract

Ensuring data ownership and traceability of unauthorised redistribution are central to safeguarding intellectual property in shared data environments. Data fingerprinting addresses these challenges by embedding recipient-specific marks into the data, typically via content modifications. We propose NCorr-FP, a Neighbourhood-based Correlation-preserving Fingerprinting system for structured tabular data that preserves the statistical fidelity of data. The method uses local record similarity and density estimation to guide the insertion of fingerprint bits. The embedding logic is then reversed to extract the fingerprint from a potentially modified dataset. Extensive experiments confirm its effectiveness, fidelity, utility, and robustness. Results show that fingerprints are virtually imperceptible, with minute Hellinger distances and KL divergences, even at high embedding rates. The system also maintains high data utility for downstream predictive tasks. The method achieves 100% detection confidence under substantial data deletions and remains robust against adaptive- and collusion attacks. Satisfying all these requirements concurrently on mixed-type datasets highlights the strong applicability of NCorr-FP to real-world data settings.

Authors: Tanja Šarčević, Andreas Rauber, and Rudolf Mayer

Links

Paper
MLDM – SBA Research Group