An Evaluation on Robustness and Utility of Fingerprinting Schemes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

An Evaluation on Robustness and Utility of Fingerprinting Schemes

Tanja Šarčević
  • Function : Author
  • PersonId : 1067022
Rudolf Mayer
  • Function : Author
  • PersonId : 1066993


Fingerprinting of data is a method to embed a traceable marker into the data to identify which specific recipient a certain copy of the data set has been released to. This is crucial for releasing data sets to third parties, especially if the release involves a fee, or if the data contains sensitive information due to which further sharing and potential subsequent leaks should be discouraged and deterred from. Fingerprints generally involve distorting the data set to a certain degree, in a trade off to preserve the utility of the data versus the robustness and traceability of the fingerprint. In this paper, we will thus compare several approaches for fingerprinting for their robustness against various types of attacks, such as subset or collusion attacks. We further evaluate the effects the fingerprinting has on the utility of the datasets, specifically for Machine Learning tasks.
Fichier principal
Vignette du fichier
485369_1_En_14_Chapter.pdf (291.33 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02520057 , version 1 (26-03-2020)





Tanja Šarčević, Rudolf Mayer. An Evaluation on Robustness and Utility of Fingerprinting Schemes. 3rd International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2019, Canterbury, United Kingdom. pp.209-228, ⟨10.1007/978-3-030-29726-8_14⟩. ⟨hal-02520057⟩
18 View
17 Download



Gmail Facebook Twitter LinkedIn More