PAC Privacy: Automatic Privacy Measurement and Control of Data Processing
Hanshen Xiao, Srinivas Devadas

TL;DR
This paper introduces PAC Privacy, a new information-theoretic privacy framework that automatically measures and controls data privacy during processing, offering instance-based guarantees and practical utility advantages over traditional methods.
Contribution
It proposes PAC Privacy as a novel, automatable privacy measure with composability and applicability to complex data processing, differing from classical cryptography and differential privacy.
Findings
Automated Monte-Carlo analysis framework for PAC Privacy guarantees.
PAC Privacy allows for lower perturbation in high-dimensional data.
Provides simple composition bounds for privacy guarantees.
Abstract
We propose and study a new privacy definition, termed Probably Approximately Correct (PAC) Privacy. PAC Privacy characterizes the information-theoretic hardness to recover sensitive data given arbitrary information disclosure/leakage during/after any processing. Unlike the classic cryptographic definition and Differential Privacy (DP), which consider the adversarial (input-independent) worst case, PAC Privacy is a simulatable metric that quantifies the instance-based impossibility of inference. A fully automatic analysis and proof generation framework is proposed: security parameters can be produced with arbitrarily high confidence via Monte-Carlo simulation for any black-box data processing oracle. This appealing automation property enables analysis of complicated data processing, where the worst-case proof in the classic privacy regime could be loose or even intractable. Moreover, we…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPrivacy-Preserving Technologies in Data · Cryptography and Data Security · Adversarial Robustness in Machine Learning
