Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spaces

by   Ahmad-Reza Ehyaei, et al.
Max Planck Society
Universität Tübingen
Montréal Institute of Learning Algorithms

As responsible AI gains importance in machine learning algorithms, properties such as fairness, adversarial robustness, and causality have received considerable attention in recent years. However, despite their individual significance, there remains a critical gap in simultaneously exploring and integrating these properties. In this paper, we propose a novel approach that examines the relationship between individual fairness, adversarial robustness, and structural causal models in heterogeneous data spaces, particularly when dealing with discrete sensitive attributes. We use causal structural models and sensitive attributes to create a fair metric and apply it to measure semantic similarity among individuals. By introducing a novel causal adversarial perturbation and applying adversarial training, we create a new regularizer that combines individual fairness, causality, and robustness in the classifier. Our method is evaluated on both real-world and synthetic datasets, demonstrating its effectiveness in achieving an accurate classifier that simultaneously exhibits fairness, adversarial robustness, and causal awareness.


page 7

page 15


Enhancing Model Robustness and Fairness with Causality: A Regularization Approach

Recent work has raised concerns on the risk of spurious correlations and...

Causal Reasoning for Algorithmic Fairness

In this work, we argue for the importance of causal reasoning in creatin...

PC-Fairness: A Unified Framework for Measuring Causality-based Fairness

A recent trend of fair machine learning is to define fairness as causali...

Causal Discovery for Fairness

It is crucial to consider the social and ethical consequences of AI and ...

Causal intersectionality for fair ranking

In this paper we propose a causal modeling approach to intersectional fa...

Robustness Implies Fairness in Casual Algorithmic Recourse

Algorithmic recourse aims to disclose the inner workings of the black-bo...

Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives

The trustworthiness of machine learning has emerged as a critical topic ...

Please sign up or login with your details

Forgot password? Click here to reset