Gizlilik: veriyi anonim sanmak

İsmi silmek anonimleştirmez, ve modelin kendisi eğitim verisini sızdırır. Dördü de ölçülüyor.

Kaynaklar

• Sweeney, L. 2002 · k-Anonymity: A Model for Protecting Privacy · Int. J. of Uncertainty, Fuzziness and Knowledge-Based Systems, 10(5)
• Shokri, R. et al. 2017 · Membership Inference Attacks Against Machine Learning Models · IEEE S&P 2017
• Dwork, C. & Roth, A. 2014 · The Algorithmic Foundations of Differential Privacy · Foundations and Trends in Theoretical Computer Science, 9(3-4)