Automated Test Generation to Detect Individual Discrimination in AI Models

Abstract

Dependability on AI models is of utmost importance to ensure full acceptance of the AI systems. One of the key aspects of the dependable AI system is to ensure that all its decisions are fair and not biased towards any individual. In this paper, we address the problem of detecting whether a model has an individual discrimination. Such a discrimination exists when two individuals who differ only in the values of their protected attributes (such as, gender/race) while the values of their non-protected ones are exactly the same, get different decisions. Measuring individual discrimination requires an exhaustive testing, which is infeasible for a non-trivial system. In this paper, we present an automated technique to generate test inputs, which is geared towards finding individual discrimination. Our technique combines the well-known technique called symbolic execution along with the local explainability for generation of effective test cases. Our experimental results clearly demonstrate that our technique produces 3.72 times more successful test cases than the existing state-of-the-art across all our chosen benchmarks.

References in corpus (6)

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Fairness Testing: Testing Software for Discrimination
• Testing Deep Neural Networks
• Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models
• Symbolic Execution for Deep Neural Networks
• Concolic Testing for Deep Neural Networks

Cited by in corpus (6)

• A Survey on AI Assurance
• Machine Learning Testing: Survey, Landscapes and Horizons
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Causal Testing: Finding Defects' Root Causes
• Probabilistic Verification of Neural Networks Against Group Fairness
• Counterfactual Situation Testing: From Single to Multidimensional Discrimination