Automated Test Generation to Detect Individual Discrimination in AI Models

TL;DR

This paper introduces an automated test generation method combining symbolic execution and explainability to detect individual discrimination in AI models, significantly improving test case effectiveness.

Contribution

It presents a novel automated technique for generating test inputs to detect individual discrimination, outperforming existing methods in effectiveness.

Findings

Produces 3.72 times more successful test cases than previous methods

Effectively identifies individual discrimination in AI models

Uses symbolic execution and local explainability for test generation

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.