Achieving Transparency Report Privacy in Linear Time

TL;DR

This paper introduces a linear-time optimal privacy scheme for transparency reports that balances privacy, utility, and fairness, addressing a critical gap in formal understanding of privacy impacts in algorithmic transparency.

Contribution

It proposes the first analytical framework for simultaneously analyzing privacy, utility, and fairness trade-offs in algorithmic transparency reports using linear fractional programming.

Findings

Demonstrates potential privacy hazards in transparency and fairness measures

Proposes a linear-time optimal privacy-preserving scheme for ATRs

Quantifies privacy-utility trade-offs and analyzes impact on fairness

Abstract

An accountable algorithmic transparency report (ATR) should ideally investigate the (a) transparency of the underlying algorithm, and (b) fairness of the algorithmic decisions, and at the same time preserve data subjects' privacy. However, a provably formal study of the impact to data subjects' privacy caused by the utility of releasing an ATR (that investigates transparency and fairness), is yet to be addressed in the literature. The far-fetched benefit of such a study lies in the methodical characterization of privacy-utility trade-offs for release of ATRs in public, and their consequential application-specific impact on the dimensions of society, politics, and economics. In this paper, we first investigate and demonstrate potential privacy hazards brought on by the deployment of transparency and fairness measures in released ATRs. To preserve data subjects' privacy, we then propose a linear-time optimal-privacy scheme, built upon standard linear fractional programming (LFP) theory, for announcing ATRs, subject to constraints controlling the tolerance of privacy perturbation on the utility of transparency schemes. Subsequently, we quantify the privacy-utility trade-offs induced by our scheme, and analyze the impact of privacy perturbation on fairness measures in ATRs. To the best of our knowledge, this is the first analytical work that simultaneously addresses trade-offs between the triad of privacy, utility, and fairness, applicable to algorithmic transparency reports.