Runtime monitoring of dynamic fairness properties

T Henzinger, M Karimi, K Kueffner… - Proceedings of the 2023 …, 2023 - dl.acm.org
A machine-learned system that is fair in static decision-making tasks may have biased
societal impacts in the long-run. This may happen when the system interacts with humans …

Monitoring unmanned aircraft: specification, integration, and lessons-learned

J Baumeister, B Finkbeiner, F Kohn, F Löhr… - … on Computer Aided …, 2024 - Springer
This paper reports on the integration of runtime monitoring into fully-electric aircraft designed
by Volocopter, a German aircraft manufacturer of electric multi-rotor helicopters. The runtime …

Monitoring algorithmic fairness under partial observations

TA Henzinger, K Kueffner, K Mallik - International Conference on Runtime …, 2023 - Springer
As AI and machine-learned software are used increasingly for making decisions that affect
humans, it is imperative that they remain fair and unbiased in their decisions. To …

Counterfactual Fairness With the Human in the Loop

Z Zuo, T Xie, X Tan, X Zhang, MM Khalili - openreview.net
Machine learning models have been increasingly used in human-related applications such
as healthcare, lending, and college admissions. As a result, there are growing concerns …