Beyond the Calibration Point: Mechanism Comparison in Differential Privacy

MCML Authors

Georgios Kaissis

Dr.

Principal Investigator

* Former Principal Investigator

Stefan Kolek

→ Group Gitta Kutyniok
 Mathematical Foundations of Artificial Intelligence

Daniel Rückert

Prof. Dr.

Director

Artificial Intelligence in Healthcare and Medicine

Abstract

In differentially private (DP) machine learning, the privacy guarantees of DP mechanisms are often reported and compared on the basis of a single pε,δq-pair. This practice overlooks that DP guarantees can vary substantially even between mechanisms sharing a given pε,δq, and potentially introduces privacy vulnerabilities which can remain undetected. This motivates the need for robust, rigorous methods for comparing DP guarantees in such cases. Here, we introduce the ∆-divergence between mechanisms which quantifies the worst-case excess privacy vulnerability of choosing one mechanism over another in terms of pε,δq, f-DP and in terms of a newly presented Bayesian interpretation. Moreover, as a generalisation of the Blackwell theorem, it is endowed with strong decision-theoretic foundations. Through application examples, we show that our techniques can facilitate informed decision-making and reveal gaps in the current understanding of privacy risks, as current practices in DP-SGD often result in choosing mechanisms with high excess privacy vulnerabilities.

inproceedings KKB+24

---

ICML 2024

41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024.

---

Authors

G. Kaissis • S. Kolek • B. Balle • J. Hayes • D. Rückert

---

Links

URL

---

In Collaboration

 Google

---

Research Areas

 A2 | Mathematical Foundations

 C1 | Medicine