Carnegie Mellon University

Block Center for Technology and Society

Block Center for Technology and Society › Responsible AI › Research › Audit Studies

Responsible AI Research

Audit Studies

Approaches and tools to audit AI systems for issues such as unfairness and harmful consequences.

2022

A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms

Akpinar, Heidari, Wu, Zhu, et al (2022)

Toward User-Driven Algorithm Auditing: Investigating users’ strategies for uncovering harmful algorithmic behavior

DeVos, Shen, Holstein, Eslami, et al. (2022)

2021

Discovering and Validating AI Errors With Crowdsourced Failure Reports

Hong, Cabrera, et al. (2021)

Everyday Algorithm Auditing: Understanding the Power of Everyday Users in Surfacing Harmful Algorithmic Behaviors

DeVos, Shen, Holstein, Eslami (2021)

2019

Visual Analytics for Discovering Intersectional Bias in Machine Learning

Cabrera et al. (2019)

Contact us | ResponsibleAI@cmu.edu