A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results

• URL: http://arxiv.org/abs/2405.14725v1
• Date: Thu, 23 May 2024 15:54:03 GMT
• Title: A Systematic and Formal Study of the Impact of Local Differential Privacy on Fairness: Preliminary Results
• Authors: Karima Makhlouf, Tamara Stefanovic, Heber H. Arcolezi, Catuscia Palamidessi,
• Abstract summary: Differential privacy (DP) is the predominant solution for privacy-preserving Machine learning (ML) algorithms. Recent experimental studies have shown that local DP can impact ML prediction for different subgroups of individuals. We study how the fairness of the decisions made by the ML model changes under local DP for different levels of privacy and data distributions.
• Score: 5.618541935188389
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning (ML) algorithms rely primarily on the availability of training data, and, depending on the domain, these data may include sensitive information about the data providers, thus leading to significant privacy issues. Differential privacy (DP) is the predominant solution for privacy-preserving ML, and the local model of DP is the preferred choice when the server or the data collector are not trusted. Recent experimental studies have shown that local DP can impact ML prediction for different subgroups of individuals, thus affecting fair decision-making. However, the results are conflicting in the sense that some studies show a positive impact of privacy on fairness while others show a negative one. In this work, we conduct a systematic and formal study of the effect of local DP on fairness. Specifically, we perform a quantitative study of how the fairness of the decisions made by the ML model changes under local DP for different levels of privacy and data distributions. In particular, we provide bounds in terms of the joint distributions and the privacy level, delimiting the extent to which local DP can impact the fairness of the model. We characterize the cases in which privacy reduces discrimination and those with the opposite effect. We validate our theoretical findings on synthetic and real-world datasets. Our results are preliminary in the sense that, for now, we study only the case of one sensitive attribute, and only statistical disparity, conditional statistical disparity, and equal opportunity difference.

Related papers

• Privacy at a Price: Exploring its Dual Impact on AI Fairness [24.650648702853903]
  We show that differential privacy in machine learning models can unequally impact separate demographic subgroups regarding prediction accuracy. This leads to a fairness concern, and manifests as biased performance. implementing gradient clipping in the differentially private gradient descent ML method can mitigate the negative impact of DP noise on fairness.
  arXiv  Detail & Related papers  (2024-04-15T00:23:41Z)
• On the Impact of Multi-dimensional Local Differential Privacy on Fairness [5.237044436478256]
  We examine the impact of differential privacy (LDP) in the presence of several sensitive attributes on fairness. In particular, multi-dimensional LDP is an efficient approach to reduce disparity. We summarize our findings in the form of recommendations to guide practitioners in adopting effective privacy-preserving practices.
  arXiv  Detail & Related papers  (2023-12-07T16:17:34Z)
• Causal Inference with Differentially Private (Clustered) Outcomes [16.166525280886578]
  Estimating causal effects from randomized experiments is only feasible if participants agree to reveal their responses. We suggest a new differential privacy mechanism, Cluster-DP, which leverages any given cluster structure. We show that, depending on an intuitive measure of cluster quality, we can improve the variance loss while maintaining our privacy guarantees.
  arXiv  Detail & Related papers  (2023-08-02T05:51:57Z)
• (Local) Differential Privacy has NO Disparate Impact on Fairness [4.157415305926584]
  Local Differential Privacy (LDP) has gained widespread adoption in real-world applications. This paper empirically studies the impact of collecting multiple sensitive attributes under LDP on fairness.
  arXiv  Detail & Related papers  (2023-04-25T14:18:12Z)
• 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)
• 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)
• Partial sensitivity analysis in differential privacy [58.730520380312676]
  We investigate the impact of each input feature on the individual's privacy loss. We experimentally evaluate our approach on queries over private databases. We also explore our findings in the context of neural network training on synthetic data.
  arXiv  Detail & Related papers  (2021-09-22T08:29:16Z)
• Decision Making with Differential Privacy under a Fairness Lens [65.16089054531395]
  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.
  arXiv  Detail & Related papers  (2021-05-16T21:04:19Z)
• Robustness Threats of Differential Privacy [70.818129585404]
  We experimentally demonstrate that networks, trained with differential privacy, in some settings might be even more vulnerable in comparison to non-private versions. We study how the main ingredients of differentially private neural networks training, such as gradient clipping and noise addition, affect the robustness of the model.
  arXiv  Detail & Related papers  (2020-12-14T18:59:24Z)
• 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)

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.