{"year":"2023","isi":1,"file_date_updated":"2023-07-18T07:43:10Z","acknowledgement":"The authors would like to thank the anonymous reviewers for their valuable comments and helpful suggestions. This work is supported by the European Research Council under Grant No.: ERC-2020-AdG 101020093.","project":[{"_id":"62781420-2b32-11ec-9570-8d9b63373d4d","name":"Vigilant Algorithmic Monitoring of Software","grant_number":"101020093","call_identifier":"H2020"}],"ddc":["000"],"publication":"FAccT '23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency","has_accepted_license":"1","author":[{"orcid":"0000-0002-2985-7724","id":"40876CD8-F248-11E8-B48F-1D18A9856A87","full_name":"Henzinger, Thomas A","first_name":"Thomas A","last_name":"Henzinger"},{"full_name":"Karimi, Mahyar","first_name":"Mahyar","last_name":"Karimi"},{"first_name":"Konstantin","last_name":"Kueffner","full_name":"Kueffner, Konstantin","id":"8121a2d0-dc85-11ea-9058-af578f3b4515","orcid":"0000-0001-8974-2542"},{"orcid":"0000-0001-9864-7475","first_name":"Kaushik","last_name":"Mallik","full_name":"Mallik, Kaushik","id":"0834ff3c-6d72-11ec-94e0-b5b0a4fb8598"}],"page":"604-614","doi":"10.1145/3593013.3594028","publication_identifier":{"isbn":["9781450372527"]},"external_id":{"arxiv":["2305.04699"],"isi":["001062819300057"]},"conference":{"end_date":"2023-06-15","location":"Chicago, IL, United States","name":"FAccT: Conference on Fairness, Accountability and Transparency","start_date":"2023-06-12"},"citation":{"ista":"Henzinger TA, Karimi M, Kueffner K, Mallik K. 2023. Runtime monitoring of dynamic fairness properties. FAccT ’23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency. FAccT: Conference on Fairness, Accountability and Transparency, 604–614.","apa":"Henzinger, T. A., Karimi, M., Kueffner, K., &#38; Mallik, K. (2023). Runtime monitoring of dynamic fairness properties. In <i>FAccT ’23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency</i> (pp. 604–614). Chicago, IL, United States: Association for Computing Machinery. <a href=\"https://doi.org/10.1145/3593013.3594028\">https://doi.org/10.1145/3593013.3594028</a>","chicago":"Henzinger, Thomas A, Mahyar Karimi, Konstantin Kueffner, and Kaushik Mallik. “Runtime Monitoring of Dynamic Fairness Properties.” In <i>FAccT ’23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency</i>, 604–14. Association for Computing Machinery, 2023. <a href=\"https://doi.org/10.1145/3593013.3594028\">https://doi.org/10.1145/3593013.3594028</a>.","ama":"Henzinger TA, Karimi M, Kueffner K, Mallik K. Runtime monitoring of dynamic fairness properties. In: <i>FAccT ’23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency</i>. Association for Computing Machinery; 2023:604-614. doi:<a href=\"https://doi.org/10.1145/3593013.3594028\">10.1145/3593013.3594028</a>","short":"T.A. Henzinger, M. Karimi, K. Kueffner, K. Mallik, in:, FAccT ’23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, Association for Computing Machinery, 2023, pp. 604–614.","mla":"Henzinger, Thomas A., et al. “Runtime Monitoring of Dynamic Fairness Properties.” <i>FAccT ’23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency</i>, Association for Computing Machinery, 2023, pp. 604–14, doi:<a href=\"https://doi.org/10.1145/3593013.3594028\">10.1145/3593013.3594028</a>.","ieee":"T. A. Henzinger, M. Karimi, K. Kueffner, and K. Mallik, “Runtime monitoring of dynamic fairness properties,” in <i>FAccT ’23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency</i>, Chicago, IL, United States, 2023, pp. 604–614."},"ec_funded":1,"_id":"13228","language":[{"iso":"eng"}],"user_id":"2DF688A6-F248-11E8-B48F-1D18A9856A87","date_created":"2023-07-16T22:01:09Z","oa_version":"Published Version","oa":1,"scopus_import":"1","publisher":"Association for Computing Machinery","status":"public","title":"Runtime monitoring of dynamic fairness properties","quality_controlled":"1","day":"12","type":"conference","file":[{"checksum":"96c759db9cdf94b81e37871a66a6ff48","relation":"main_file","content_type":"application/pdf","access_level":"open_access","creator":"dernst","file_name":"2023_ACM_HenzingerT.pdf","date_updated":"2023-07-18T07:43:10Z","success":1,"file_id":"13245","date_created":"2023-07-18T07:43:10Z","file_size":4100596}],"date_updated":"2023-12-13T11:30:31Z","tmp":{"image":"/images/cc_by.png","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","short":"CC BY (4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"article_processing_charge":"No","month":"06","date_published":"2023-06-12T00:00:00Z","publication_status":"published","abstract":[{"text":"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 and feedback patterns emerge, reinforcing old biases in the system and creating new biases. While existing works try to identify and mitigate long-run biases through smart system design, we introduce techniques for monitoring fairness in real time. Our goal is to build and deploy a monitor that will continuously observe a long sequence of events generated by the system in the wild, and will output, with each event, a verdict on how fair the system is at the current point in time. The advantages of monitoring are two-fold. Firstly, fairness is evaluated at run-time, which is important because unfair behaviors may not be eliminated a priori, at design-time, due to partial knowledge about the system and the environment, as well as uncertainties and dynamic changes in the system and the environment, such as the unpredictability of human behavior. Secondly, monitors are by design oblivious to how the monitored system is constructed, which makes them suitable to be used as trusted third-party fairness watchdogs. They function as computationally lightweight statistical estimators, and their correctness proofs rely on the rigorous analysis of the stochastic process that models the assumptions about the underlying dynamics of the system. We show, both in theory and experiments, how monitors can warn us (1) if a bank’s credit policy over time has created an unfair distribution of credit scores among the population, and (2) if a resource allocator’s allocation policy over time has made unfair allocations. Our experiments demonstrate that the monitors introduce very low overhead. We believe that runtime monitoring is an important and mathematically rigorous new addition to the fairness toolbox.","lang":"eng"}],"department":[{"_id":"ToHe"}]}