Automated Directed Fairness Testing

Abstract

Fairness is a critical trait in decision making. As machine-learning models are increasingly being used in sensitive application domains (e.g. education and employment) for decision making, it is crucial that the decisions computed by such models are free of unintended bias. But how can we automatically validate the fairness of arbitrary machine-learning models? For a given machine-learning model and a set of sensitive input parameters, our AEQUITAS approach automatically discovers discriminatory inputs that highlight fairness violation. At the core of AEQUITAS are three novel strategies to employ probabilistic search over the input space with the objective of uncovering fairness violation. Our AEQUITAS approach leverages inherent robustness property in common machine-learning models to design and implement scalable test generation methodologies. An appealing feature of our generated test inputs is that they can be systematically added to the training set of the underlying model and improve its fairness. To this end, we design a fully automated module that guarantees to improve the fairness of the underlying model. We implemented AEQUITAS and we have evaluated it on six state-of-the-art classifiers, including a classifier that was designed with fairness constraints. We show that AEQUITAS effectively generates inputs to uncover fairness violation in all the subject classifiers and systematically improves the fairness of the respective models using the generated test inputs. In our evaluation, AEQUITAS generates up to 70% discriminatory inputs (w.r.t. the total number of inputs generated) and leverages these inputs to improve the fairness up to 94%.

arXiv commentIn Proceedings of the 2018 33rd ACM/IEEE International Conference on Automated Software Engineering (ASE 18), September 3-7, 2018, Montpellier, France

References in corpus (5)

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Fairness Testing: Testing Software for Discrimination
• Fairness Constraints: Mechanisms for Fair Classification
• DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars
• Satisfying Real-world Goals with Dataset Constraints

Cited by in corpus (33)

• Fast Parallel Hypertree Decompositions in Logarithmic Recursion Depth
• Bias in Machine Learning Software: Why? How? What to do?
• Testing Deep Neural Networks
• Machine Learning Testing: Survey, Landscapes and Horizons
• Fair Preprocessing: Towards Understanding Compositional Fairness of Data Transformers in Machine Learning Pipeline
• Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
• Software Engineering for AI-Based Systems: A Survey
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Fairness-aware Configuration of Machine Learning Libraries
• Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing
• Towards Safe Machine Learning for CPS: Infer Uncertainty from Training Data
• Making Fair ML Software using Trustworthy Explanation
• BiasRV: Uncovering Biased Sentiment Predictions at Runtime
• To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods
• Metamorphic Testing for Object Detection Systems
• Software Engineering for Fairness: A Case Study with Hyperparameter Optimization
• Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoML
• Adversarial Sampling for Fairness Testing in Deep Neural Network
• Smoke Testing for Machine Learning: Simple Tests to Discover Severe Defects
• Removing biased data to improve fairness and accuracy
• Fair-SSL: Building fair ML Software with less data
• Fairness Testing of Deep Image Classification with Adequacy Metrics
• Vertical Allocation-based Fair Exposure Amortizing in Ranking
• ShapeFlow: Dynamic Shape Interpreter for TensorFlow
• Perfectly Parallel Fairness Certification of Neural Networks
• An Epistemic Approach to the Formal Specification of Statistical Machine Learning
• Probabilistic Verification of Neural Networks Against Group Fairness
• Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
• SOCRATES: Towards a Unified Platform for Neural Network Analysis
• Explaining Image Classifiers using Statistical Fault Localization
• Fairness-guided SMT-based Rectification of Decision Trees and Random Forests
• Correct-By-Construction: Certified Individual Fairness through Neural Network Training
• Uncovering Discrimination Clusters: Quantifying and Explaining Systematic Fairness Violations