Adaptive Attacks and Targeted Fingerprinting of Relational Data
From December 17-20, 2022 the IEEE Big Data conference took place in Osaka, Japan. Tanja Šarčević, researcher at SBA Research, held a talk about adaptive attacks and targeted fingerprinting of relational data.
Titel
Adaptive Attacks and Targeted Fingerprinting of Relational Data
Authors
Tanja Šarčević, Rudolf Mayer, Andreas Rauber
Report
IEEE Big Data
Abstract
Fingerprinting is a method of embedding a traceable mark into digital data to (i) verify the owner and (ii) identify the recipient of a released copy of a data set. This is crucial when releasing data to third parties, especially if it involves a fee, or if the data is of sensitive nature and further sharing and leaks should be discouraged and deterred from. A fingerprint is required to (i) be robust against modifications to the data to achieve successful ownership protection, while (ii) affecting the quality and utility of the data as little as possible. So far, literature mostly assumes attackers with rather limited capabilities who perform random modification to the dataset. With a certain task in mind to perform on the data, the attacker can however perform an adaptive and targeted attack that maximises its chances of removing or invalidating the fingerprint, while reducing the data utility the least. In the same line, the data owner can optimise the robustness of the scheme by anticipating a specific focus of the attacker and focusing the fingerprint embedding on the most valuable parts of the data. In this paper, we, therefore, provide an in-depth discussion on threat models, targeted attacks and adaptive defences. We further demonstrate the impact of targeted attacks on classical and, in comparison, adaptive fingerprinting in an empirical manner. Index Terms—Fingerprinting, Intellectual Property