Abstract
Bias in decisions made by modern software is becoming a common and serious problem. We present Themis, an automated test suite generator to measure two types of discrimination, including causal relationships between sensitive inputs and program behavior. We explain how Themis can measure discrimination and aid its debugging, describe a set of optimizations Themis uses to reduce test suite size, and demonstrate Themis' effectiveness on open-source software.
Author supplied keywords
Cite
CITATION STYLE
Angell, R., Johnson, B., Brun, Y., & Meliou, A. (2018). Themis: Automatically testing software for discrimination. In ESEC/FSE 2018 - Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (pp. 871–875). Association for Computing Machinery, Inc. https://doi.org/10.1145/3236024.3264590
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.