Achieving Transparency Report Privacy in Linear Time

03/31/2021
by   Chien-Lun Chen, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 8

page 17

page 19

page 23

page 28

page 29

page 30

page 33

09/08/2021

On the Fundamental Trade-offs in Learning Invariant Representations

Many applications of representation learning, such as privacy-preservati...
12/15/2020

Beyond Privacy Trade-offs with Structured Transparency

Many socially valuable activities depend on sensitive information, such ...
01/02/2021

Dimensions of Transparency in NLP Applications

Broader transparency in descriptions of and communication regarding AI s...
12/24/2020

Quantifying the Privacy-Utility Trade-offs in COVID-19 Contact Tracing Apps

How to contain the spread of the COVID-19 virus is a major concern for m...
11/30/2018

On the Difficulties of Incentivizing Online Privacy through Transparency: A Qualitative Survey of the German Health Insurance Market

Today, online privacy is the domain of regulatory measures and privacy-e...
10/09/2017

Optimization of Privacy-Utility Trade-offs under Informational Self-determination

The pervasiveness of Internet of Things results in vast volumes of perso...
09/19/2016

Inherent Trade-Offs in the Fair Determination of Risk Scores

Recent discussion in the public sphere about algorithmic classification ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.