Decision Making with Differential Privacy under a Fairness Lens
- URL: http://arxiv.org/abs/2105.07513v1
- Date: Sun, 16 May 2021 21:04:19 GMT
- Title: Decision Making with Differential Privacy under a Fairness Lens
- Authors: Ferdinando Fioretto, Cuong Tran, Pascal Van Hentenryck
- Abstract summary: The U.S. Census Bureau releases data sets and statistics about groups of individuals that are used as input to a number of critical decision processes.
To conform to privacy and confidentiality requirements, these agencies are often required to release privacy-preserving versions of the data.
This paper studies the release of differentially private data sets and analyzes their impact on some critical resource allocation tasks under a fairness perspective.
- Score: 44.4747903763245
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Agencies, such as the U.S. Census Bureau, release data sets and statistics
about groups of individuals that are used as input to a number of critical
decision processes. To conform to privacy and confidentiality requirements,
these agencies are often required to release privacy-preserving versions of the
data. This paper studies the release of differentially private data sets and
analyzes their impact on some critical resource allocation tasks under a
fairness perspective. {The paper shows that, when the decisions take as input
differentially private data}, the noise added to achieve privacy
disproportionately impacts some groups over others. The paper analyzes the
reasons for these disproportionate impacts and proposes guidelines to mitigate
these effects. The proposed approaches are evaluated on critical decision
problems that use differentially private census data.
Related papers
- A Summary of Privacy-Preserving Data Publishing in the Local Setting [0.6749750044497732]
Statistical Disclosure Control aims to minimize the risk of exposing confidential information by de-identifying it.
We outline the current privacy-preserving techniques employed in microdata de-identification, delve into privacy measures tailored for various disclosure scenarios, and assess metrics for information loss and predictive performance.
arXiv Detail & Related papers (2023-12-19T04:23:23Z) - Privately Answering Queries on Skewed Data via Per Record Differential Privacy [8.376475518184883]
We propose a privacy formalism, per-record zero concentrated differential privacy (PzCDP)
Unlike other formalisms which provide different privacy losses to different records, PzCDP's privacy loss depends explicitly on the confidential data.
arXiv Detail & Related papers (2023-10-19T15:24:49Z) - Enabling Trade-offs in Privacy and Utility in Genomic Data Beacons and
Summary Statistics [26.99521354120141]
We introduce optimization-based approaches to explicitly trade off the utility of summary data or Beacon responses and privacy.
In the first, an attacker applies a likelihood-ratio test to make membership-inference claims.
In the second, an attacker uses a threshold that accounts for the effect of the data release on the separation in scores between individuals.
arXiv Detail & Related papers (2023-01-11T19:16:13Z) - How Do Input Attributes Impact the Privacy Loss in Differential Privacy? [55.492422758737575]
We study the connection between the per-subject norm in DP neural networks and individual privacy loss.
We introduce a novel metric termed the Privacy Loss-Input Susceptibility (PLIS) which allows one to apportion the subject's privacy loss to their input attributes.
arXiv Detail & Related papers (2022-11-18T11:39:03Z) - Algorithms with More Granular Differential Privacy Guarantees [65.3684804101664]
We consider partial differential privacy (DP), which allows quantifying the privacy guarantee on a per-attribute basis.
In this work, we study several basic data analysis and learning tasks, and design algorithms whose per-attribute privacy parameter is smaller that the best possible privacy parameter for the entire record of a person.
arXiv Detail & Related papers (2022-09-08T22:43:50Z) - Post-processing of Differentially Private Data: A Fairness Perspective [53.29035917495491]
This paper shows that post-processing causes disparate impacts on individuals or groups.
It analyzes two critical settings: the release of differentially private datasets and the use of such private datasets for downstream decisions.
It proposes a novel post-processing mechanism that is (approximately) optimal under different fairness metrics.
arXiv Detail & Related papers (2022-01-24T02:45:03Z) - Differentially Private and Fair Deep Learning: A Lagrangian Dual
Approach [54.32266555843765]
This paper studies a model that protects the privacy of the individuals sensitive information while also allowing it to learn non-discriminatory predictors.
The method relies on the notion of differential privacy and the use of Lagrangian duality to design neural networks that can accommodate fairness constraints.
arXiv Detail & Related papers (2020-09-26T10:50:33Z) - Neither Private Nor Fair: Impact of Data Imbalance on Utility and
Fairness in Differential Privacy [5.416049433853457]
We study how different levels of imbalance in the data affect the accuracy and the fairness of the decisions made by the model.
We demonstrate that even small imbalances and loose privacy guarantees can cause disparate impacts.
arXiv Detail & Related papers (2020-09-10T18:35:49Z) - Differential Privacy of Hierarchical Census Data: An Optimization
Approach [53.29035917495491]
Census Bureaus are interested in releasing aggregate socio-economic data about a large population without revealing sensitive information about any individual.
Recent events have identified some of the privacy challenges faced by these organizations.
This paper presents a novel differential-privacy mechanism for releasing hierarchical counts of individuals.
arXiv Detail & Related papers (2020-06-28T18:19:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.