mlsanityData to 7 Oct 2026

Generalised Likelihood Ratio Testing Adversaries through the Differential Privacy Lens

arXiv 2210.13028 ↗First posted 24 Oct 2022cs.CR cs.AI stat.APcited by 0

Not on the map. Why?

Abstract (arXiv)

Differential Privacy (DP) provides tight upper bounds on the capabilities of optimal adversaries, but such adversaries are rarely encountered in practice. Under the hypothesis testing/membership inference interpretation of DP, we examine the Gaussian mechanism and relax the usual assumption of a Neyman-Pearson-Optimal (NPO) adversary to a Generalized Likelihood Test (GLRT) adversary. This mild relaxation leads to improved privacy guarantees, which we express in the spirit of Gaussian DP and (varepsilon, δ)-DP, including composition and sub-sampling results. We evaluate our results numerically and find them to match the theoretical upper bounds.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 13 of its 23 references that are in the map. First posted on arXiv 24 Oct 2022.

Builds on

13 of 23 references.

References · 13

  1. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  2. 2021Membership Inference Attacks From First Principlescited by 839
  3. 2013The Composition Theorem for Differential Privacycited by 290
  4. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 265
  5. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  6. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 213
  7. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  8. 2021Numerical Composition of Differential Privacycited by 174
  9. 2021Optimal Accounting of Differential Privacy via Characteristic Functioncited by 83
  10. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 79
  11. 2022Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanismscited by 19
  12. 2022Edgeworth Accountant: An Analytical Approach to Differential Privacy Compositioncited by 14
1 more
  1. 2021Generalization Techniques Empirically Outperform Differential Privacy against Membership Inferencecited by 5

Built on by

Not cited yet.