Breaking Fair Binary Classification with Optimal Flipping Attacks
Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the training set is corrupted. In this work, we study the minimum amount of data corruption required for a successful flipping attack. First, we find lower/upper bounds on this quantity and show that these bounds are tight when the target model is the unique unconstrained risk minimizer. Second, we propose a computationally efficient data poisoning attack algorithm that can compromise the performance of fair learning algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
Binary ClassificationClassificationData PoisoningFairnessSimilar Papers 제목 키워드 기반
iFlipper: Label Flipping for Individual Fairness
As machine learning becomes prevalent, mitigating any unfairness present in the training data becomes critical. Among the various notions of fairness, this paper focuses on the well-known individual fairness, which state…
FairnessStatistical Guarantees for Fairness Aware Plug-In Algorithms
A plug-in algorithm to estimate Bayes Optimal Classifiers for fairness-aware binary classification has been proposed in (Menon & Williamson, 2018). However, the statistical efficacy of their approach has not been establi…
Binary ClassificationFairnessOptimal Fairness under Local Differential Privacy
We investigate how to optimally design local differential privacy (LDP) mechanisms that reduce data unfairness and thereby improve fairness in downstream classification. We first derive a closed-form optimal mechanism fo…
Reinforcement Learning for Channel Coding: Learned Bit-Flipping Decoding
In this paper, we use reinforcement learning to find effective decoding strategies for binary linear codes. We start by reviewing several iterative decoding algorithms that involve a decision-making process at each step,…
Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
We study the problem of fair binary classification using the notion of Equal Opportunity. It requires the true positive rate to distribute equally across the sensitive groups. Within this setting we show that the fair op…
Binary ClassificationClassificationFairnessGeneral Classification