TESTSGD: Interpretable Testing of Neural Networks Against Subtle Group Discrimination

by   Mengdi Zhang, et al.

Discrimination has been shown in many machine learning applications, which calls for sufficient fairness testing before their deployment in ethic-relevant domains such as face recognition, medical diagnosis and criminal sentence. Existing fairness testing approaches are mostly designed for identifying individual discrimination, i.e., discrimination against individuals. Yet, as another widely concerning type of discrimination, testing against group discrimination, mostly hidden, is much less studied. To address the gap, in this work, we propose TESTSGD, an interpretable testing approach which systematically identifies and measures hidden (which we call `subtle' group discrimination of a neural network characterized by conditions over combinations of the sensitive features. Specifically, given a neural network, TESTSGDfirst automatically generates an interpretable rule set which categorizes the input space into two groups exposing the model's group discrimination. Alongside, TESTSGDalso provides an estimated group fairness score based on sampling the input space to measure the degree of the identified subtle group discrimination, which is guaranteed to be accurate up to an error bound. We evaluate TESTSGDon multiple neural network models trained on popular datasets including both structured data and text data. The experiment results show that TESTSGDis effective and efficient in identifying and measuring such subtle group discrimination that has never been revealed before. Furthermore, we show that the testing results of TESTSGDcan guide generation of new samples to mitigate such discrimination through retraining with negligible accuracy drop.


page 1

page 2

page 3

page 4


Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling

Although deep learning has demonstrated astonishing performance in many ...

Fairness Testing: Testing Software for Discrimination

This paper defines software fairness and discrimination and develops a t...

Probabilistic Verification of Neural Networks Against Group Fairness

Fairness is crucial for neural networks which are used in applications w...

Removing Algorithmic Discrimination (With Minimal Individual Error)

We address the problem of correcting group discriminations within a scor...

SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning

We propose a new discrimination-aware learning method to improve both ac...

Aleatoric and Epistemic Discrimination in Classification

Machine learning (ML) models can underperform on certain population grou...

What's Sex Got To Do With Machine Learning

Debate about fairness in machine learning has largely centered around co...

Please sign up or login with your details

Forgot password? Click here to reset