Fair Classification with Adversarial Perturbations
- URL: http://arxiv.org/abs/2106.05964v1
- Date: Thu, 10 Jun 2021 17:56:59 GMT
- Title: Fair Classification with Adversarial Perturbations
- Authors: L. Elisa Celis, Anay Mehrotra, Nisheeth K. Vishnoi
- Abstract summary: We study fair classification in the presence of an omniscient adversary that, given an $eta$, is allowed to choose an arbitrary $eta$-fraction of the training samples and arbitrarily perturb their protected attributes.
Our main contribution is an optimization framework to learn fair classifiers in this adversarial setting that comes with provable guarantees on accuracy and fairness.
We prove near-tightness of our framework's guarantees for natural hypothesis classes: no algorithm can have significantly better accuracy and any algorithm with better fairness must have lower accuracy.
- Score: 35.030329189029246
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study fair classification in the presence of an omniscient adversary that,
given an $\eta$, is allowed to choose an arbitrary $\eta$-fraction of the
training samples and arbitrarily perturb their protected attributes. The
motivation comes from settings in which protected attributes can be incorrect
due to strategic misreporting, malicious actors, or errors in imputation; and
prior approaches that make stochastic or independence assumptions on errors may
not satisfy their guarantees in this adversarial setting. Our main contribution
is an optimization framework to learn fair classifiers in this adversarial
setting that comes with provable guarantees on accuracy and fairness. Our
framework works with multiple and non-binary protected attributes, is designed
for the large class of linear-fractional fairness metrics, and can also handle
perturbations besides protected attributes. We prove near-tightness of our
framework's guarantees for natural hypothesis classes: no algorithm can have
significantly better accuracy and any algorithm with better fairness must have
lower accuracy. Empirically, we evaluate the classifiers produced by our
framework for statistical rate on real-world and synthetic datasets for a
family of adversaries.
Related papers
- Provable Optimization for Adversarial Fair Self-supervised Contrastive Learning [49.417414031031264]
This paper studies learning fair encoders in a self-supervised learning setting.
All data are unlabeled and only a small portion of them are annotated with sensitive attributes.
arXiv Detail & Related papers (2024-06-09T08:11:12Z) - 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) - Group Fairness with Uncertainty in Sensitive Attributes [34.608332397776245]
A fair predictive model is crucial to mitigate biased decisions against minority groups in high-stakes applications.
We propose a bootstrap-based algorithm that achieves the target level of fairness despite the uncertainty in sensitive attributes.
Our algorithm is applicable to both discrete and continuous sensitive attributes and is effective in real-world classification and regression tasks.
arXiv Detail & Related papers (2023-02-16T04:33:00Z) - Practical Approaches for Fair Learning with Multitype and Multivariate
Sensitive Attributes [70.6326967720747]
It is important to guarantee that machine learning algorithms deployed in the real world do not result in unfairness or unintended social consequences.
We introduce FairCOCCO, a fairness measure built on cross-covariance operators on reproducing kernel Hilbert Spaces.
We empirically demonstrate consistent improvements against state-of-the-art techniques in balancing predictive power and fairness on real-world datasets.
arXiv Detail & Related papers (2022-11-11T11:28:46Z) - Towards Fair Classification against Poisoning Attacks [52.57443558122475]
We study the poisoning scenario where the attacker can insert a small fraction of samples into training data.
We propose a general and theoretically guaranteed framework which accommodates traditional defense methods to fair classification against poisoning attacks.
arXiv Detail & Related papers (2022-10-18T00:49:58Z) - The Fairness of Credit Scoring Models [0.0]
In credit markets, screening algorithms aim to discriminate between good-type and bad-type borrowers.
This can be unintentional and originate from the training dataset or from the model itself.
We show how to formally test the algorithmic fairness of scoring models and how to identify the variables responsible for any lack of fairness.
arXiv Detail & Related papers (2022-05-20T14:20:40Z) - Fair Tree Learning [0.15229257192293202]
Various optimisation criteria combine classification performance with a fairness metric.
Current fair decision tree methods only optimise for a fixed threshold on both the classification task as well as the fairness metric.
We propose a threshold-independent fairness metric termed uniform demographic parity, and a derived splitting criterion entitled SCAFF -- Splitting Criterion AUC for Fairness.
arXiv Detail & Related papers (2021-10-18T13:40:25Z) - Beyond Individual and Group Fairness [90.4666341812857]
We present a new data-driven model of fairness that is guided by the unfairness complaints received by the system.
Our model supports multiple fairness criteria and takes into account their potential incompatibilities.
arXiv Detail & Related papers (2020-08-21T14:14:44Z) - Fair Classification with Noisy Protected Attributes: A Framework with
Provable Guarantees [43.326827444321935]
We present an optimization framework for learning a fair classifier in the presence of noisy perturbations in the protected attributes.
Our framework can be employed with a very general class of linear and linear-fractional fairness constraints.
We show that our framework can be used to attain either statistical rate or false positive rate fairness guarantees with a minimal loss in accuracy, even when the noise is large.
arXiv Detail & Related papers (2020-06-08T17:52:48Z) - Certified Robustness to Label-Flipping Attacks via Randomized Smoothing [105.91827623768724]
Machine learning algorithms are susceptible to data poisoning attacks.
We present a unifying view of randomized smoothing over arbitrary functions.
We propose a new strategy for building classifiers that are pointwise-certifiably robust to general data poisoning attacks.
arXiv Detail & Related papers (2020-02-07T21:28:30Z)
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.