@inproceedings{14454, abstract = {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 complement design-time bias mitigation measures, runtime verification techniques have been introduced recently to monitor the algorithmic fairness of deployed systems. Previous monitoring techniques assume full observability of the states of the (unknown) monitored system. Moreover, they can monitor only fairness properties that are specified as arithmetic expressions over the probabilities of different events. In this work, we extend fairness monitoring to systems modeled as partially observed Markov chains (POMC), and to specifications containing arithmetic expressions over the expected values of numerical functions on event sequences. The only assumptions we make are that the underlying POMC is aperiodic and starts in the stationary distribution, with a bound on its mixing time being known. These assumptions enable us to estimate a given property for the entire distribution of possible executions of the monitored POMC, by observing only a single execution. Our monitors observe a long run of the system and, after each new observation, output updated PAC-estimates of how fair or biased the system is. The monitors are computationally lightweight and, using a prototype implementation, we demonstrate their effectiveness on several real-world examples.}, author = {Henzinger, Thomas A and Kueffner, Konstantin and Mallik, Kaushik}, booktitle = {23rd International Conference on Runtime Verification}, isbn = {9783031442667}, issn = {1611-3349}, location = {Thessaloniki, Greece}, pages = {291--311}, publisher = {Springer Nature}, title = {{Monitoring algorithmic fairness under partial observations}}, doi = {10.1007/978-3-031-44267-4_15}, volume = {14245}, year = {2023}, } @inproceedings{13228, abstract = {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.}, author = {Henzinger, Thomas A and Karimi, Mahyar and Kueffner, Konstantin and Mallik, Kaushik}, booktitle = {FAccT '23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency}, isbn = {9781450372527}, location = {Chicago, IL, United States}, pages = {604--614}, publisher = {Association for Computing Machinery}, title = {{Runtime monitoring of dynamic fairness properties}}, doi = {10.1145/3593013.3594028}, year = {2023}, } @article{13234, abstract = {Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. We consider the problem of monitoring the classification decisions of neural networks in the presence of novel classes. For this purpose, we generalize our recently proposed abstraction-based monitor from binary output to real-valued quantitative output. This quantitative output enables new applications, two of which we investigate in the paper. As our first application, we introduce an algorithmic framework for active monitoring of a neural network, which allows us to learn new classes dynamically and yet maintain high monitoring performance. As our second application, we present an offline procedure to retrain the neural network to improve the monitor’s detection performance without deteriorating the network’s classification accuracy. Our experimental evaluation demonstrates both the benefits of our active monitoring framework in dynamic scenarios and the effectiveness of the retraining procedure.}, author = {Kueffner, Konstantin and Lukina, Anna and Schilling, Christian and Henzinger, Thomas A}, issn = {1433-2787}, journal = {International Journal on Software Tools for Technology Transfer}, pages = {575--592}, publisher = {Springer Nature}, title = {{Into the unknown: Active monitoring of neural networks (extended version)}}, doi = {10.1007/s10009-023-00711-4}, volume = {25}, year = {2023}, } @inproceedings{13310, abstract = {Machine-learned systems are in widespread use for making decisions about humans, and it is important that they are fair, i.e., not biased against individuals based on sensitive attributes. We present runtime verification of algorithmic fairness for systems whose models are unknown, but are assumed to have a Markov chain structure. We introduce a specification language that can model many common algorithmic fairness properties, such as demographic parity, equal opportunity, and social burden. We build monitors that observe a long sequence of events as generated by a given system, and output, after each observation, a quantitative estimate of how fair or biased the system was on that run until that point in time. The estimate is proven to be correct modulo a variable error bound and a given confidence level, where the error bound gets tighter as the observed sequence gets longer. Our monitors are of two types, and use, respectively, frequentist and Bayesian statistical inference techniques. While the frequentist monitors compute estimates that are objectively correct with respect to the ground truth, the Bayesian monitors compute estimates that are correct subject to a given prior belief about the system’s model. Using a prototype implementation, we show how we can monitor if a bank is fair in giving loans to applicants from different social backgrounds, and if a college is fair in admitting students while maintaining a reasonable financial burden on the society. Although they exhibit different theoretical complexities in certain cases, in our experiments, both frequentist and Bayesian monitors took less than a millisecond to update their verdicts after each observation.}, author = {Henzinger, Thomas A and Karimi, Mahyar and Kueffner, Konstantin and Mallik, Kaushik}, booktitle = {Computer Aided Verification}, isbn = {9783031377020}, issn = {1611-3349}, location = {Paris, France}, pages = {358–382}, publisher = {Springer Nature}, title = {{Monitoring algorithmic fairness}}, doi = {10.1007/978-3-031-37703-7_17}, volume = {13965}, year = {2023}, }