An Algorithm for Enhancing Privacy-Utility Tradeoff in the Privacy Funnel and Other Lift-based Measures
Mohammad Amin Zarrabian, Parastoo Sadeghi

TL;DR
This paper introduces a new privacy measure that balances privacy and utility more effectively than lift or mutual information, along with a heuristic algorithm that improves privacy-utility tradeoffs in non-convex optimization problems.
Contribution
It proposes a relaxed privacy measure based on average information density and a heuristic algorithm to optimize privacy-utility tradeoff in lift-based measures, outperforming existing methods.
Findings
Improved utility at the same privacy budget compared to previous solutions.
Applicability of the method to $ ext{l}_1$-norm and strong $oldsymbol{ ext{chi}}^2$-divergence measures.
Theoretical validation showing a perfect match with the estimated optimal utility.
Abstract
This paper investigates the privacy funnel, a privacy-utility tradeoff problem in which mutual information quantifies both privacy and utility. The objective is to maximize utility while adhering to a specified privacy budget. However, the privacy funnel represents a non-convex optimization problem, making it challenging to achieve an optimal solution. An existing proposed approach to this problem involves substituting the mutual information with the lift (the exponent of information density) and then solving the optimization. Since mutual information is the expectation of the information density, this substitution overestimates the privacy loss and results in a final smaller bound on the privacy of mutual information than what is allowed in the budget. This significantly compromises the utility. To overcome this limitation, we propose using a privacy measure that is more relaxed than…
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
