Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity

• URL: http://arxiv.org/abs/2211.02139v2
• Date: Mon, 5 Jun 2023 20:55:12 GMT
• Title: Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
• Authors: Faisal Hamman, Jiahao Chen, Sanghamitra Dutta
• Abstract summary: Existing regulations prohibit model developers from accessing protected attributes. We show that simply querying for fairness metrics can leak the protected attributes of individuals to the model developers. We propose Attribute-Conceal, a novel technique that achieves differential privacy by calibrating noise to the smooth sensitivity of our bias query.
• Score: 14.564919048514897
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Existing regulations prohibit model developers from accessing protected attributes (gender, race, etc.), often resulting in fairness assessments on populations without knowing their protected groups. In such scenarios, institutions often adopt a separation between the model developers (who train models with no access to the protected attributes) and a compliance team (who may have access to the entire dataset for auditing purposes). However, the model developers might be allowed to test their models for bias by querying the compliance team for group fairness metrics. In this paper, we first demonstrate that simply querying for fairness metrics, such as statistical parity and equalized odds can leak the protected attributes of individuals to the model developers. We demonstrate that there always exist strategies by which the model developers can identify the protected attribute of a targeted individual in the test dataset from just a single query. In particular, we show that one can reconstruct the protected attributes of all the individuals from O(Nk \log( n /Nk)) queries when Nk<<n using techniques from compressed sensing (n: size of the test dataset, Nk: size of smallest group). Our results pose an interesting debate in algorithmic fairness: should querying for fairness metrics be viewed as a neutral-valued solution to ensure compliance with regulations? Or, does it constitute a violation of regulations and privacy if the number of queries answered is enough for the model developers to identify the protected attributes of specific individuals? To address this supposed violation, we also propose Attribute-Conceal, a novel technique that achieves differential privacy by calibrating noise to the smooth sensitivity of our bias query, outperforming naive techniques such as the Laplace mechanism. We also include experimental results on the Adult dataset and synthetic data.

Related papers

• Fairness Without Harm: An Influence-Guided Active Sampling Approach [32.173195437797766]
  We aim to train models that mitigate group fairness disparity without causing harm to model accuracy. The current data acquisition methods, such as fair active learning approaches, typically require annotating sensitive attributes. We propose a tractable active data sampling algorithm that does not rely on training group annotations.
  arXiv  Detail & Related papers  (2024-02-20T07:57:38Z)
• Estimating and Implementing Conventional Fairness Metrics With Probabilistic Protected Features [7.457585597068654]
  We develop methods for measuring and reducing violations in a setting with limited attribute labels. We show our measurement method can bound the true disparity up to 5.5x tighter than previous methods in these applications.
  arXiv  Detail & Related papers  (2023-10-02T22:30:25Z)
• Client-specific Property Inference against Secure Aggregation in Federated Learning [52.8564467292226]
  Federated learning has become a widely used paradigm for collaboratively training a common model among different participants. Many attacks have shown that it is still possible to infer sensitive information such as membership, property, or outright reconstruction of participant data. We show that simple linear models can effectively capture client-specific properties only from the aggregated model updates.
  arXiv  Detail & Related papers  (2023-03-07T14:11:01Z)
• Membership Inference Attacks against Synthetic Data through Overfitting Detection [84.02632160692995]
  We argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution. We propose DOMIAS, a density-based MIA model that aims to infer membership by targeting local overfitting of the generative model.
  arXiv  Detail & Related papers  (2023-02-24T11:27:39Z)
• Fair mapping [0.0]
  We propose a novel pre-processing method based on the transformation of the distribution of protected groups onto a chosen target one. We leverage on the recent works of the Wasserstein GAN and AttGAN frameworks to achieve the optimal transport of data points. Our proposed approach, preserves the interpretability of data and can be used without defining exactly the sensitive groups.
  arXiv  Detail & Related papers  (2022-09-01T17:31:27Z)
• When Fairness Meets Privacy: Fair Classification with Semi-Private Sensitive Attributes [18.221858247218726]
  We study a novel and practical problem of fair classification in a semi-private setting. Most of the sensitive attributes are private and only a small amount of clean ones are available. We propose a novel framework FairSP that can achieve Fair prediction under the Semi-Private setting.
  arXiv  Detail & Related papers  (2022-07-18T01:10:25Z)
• SF-PATE: Scalable, Fair, and Private Aggregation of Teacher Ensembles [50.90773979394264]
  This paper studies a model that protects the privacy of individuals' sensitive information while also allowing it to learn non-discriminatory predictors. A key characteristic of the proposed model is to enable the adoption of off-the-selves and non-private fair models to create a privacy-preserving and fair model.
  arXiv  Detail & Related papers  (2022-04-11T14:42:54Z)
• Measuring Fairness of Text Classifiers via Prediction Sensitivity [63.56554964580627]
  ACCUMULATED PREDICTION SENSITIVITY measures fairness in machine learning models based on the model's prediction sensitivity to perturbations in input features. We show that the metric can be theoretically linked with a specific notion of group fairness (statistical parity) and individual fairness.
  arXiv  Detail & Related papers  (2022-03-16T15:00:33Z)
• Dikaios: Privacy Auditing of Algorithmic Fairness via Attribute Inference Attacks [0.5801044612920815]
  We propose Dikaios, a privacy auditing tool for fairness algorithms for model builders. We show that our attribute inference attacks with adaptive prediction threshold significantly outperform prior attacks.
  arXiv  Detail & Related papers  (2022-02-04T17:19:59Z)
• Measuring Fairness Under Unawareness of Sensitive Attributes: A Quantification-Based Approach [131.20444904674494]
  We tackle the problem of measuring group fairness under unawareness of sensitive attributes. We show that quantification approaches are particularly suited to tackle the fairness-under-unawareness problem.
  arXiv  Detail & Related papers  (2021-09-17T13:45:46Z)
• 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)

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.