Monitoring Algorithmic Fairness under Partial Observations

by   Thomas A. Henzinger, et al.

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.


page 1

page 2

page 3

page 4


Monitoring Algorithmic Fairness

Machine-learned systems are in widespread use for making decisions about...

Runtime Monitoring of Dynamic Fairness Properties

A machine-learned system that is fair in static decision-making tasks ma...

Towards Partial Monitoring: It is Always too Soon to Give Up

Runtime Verification is a lightweight formal verification technique. It ...

Symbolic Runtime Verification for Monitoring under Uncertainties and Assumptions

Runtime Verification deals with the question of whether a run of a syste...

On Adaptive Fairness in Software Systems

Software systems are increasingly making decisions on behalf of humans, ...

Efficient Two-Layered Monitor for Partially Synchronous Distributed Systems (Technical Report)

Monitoring distributed systems to ensure their correctness is a challeng...

BiasRV: Uncovering Biased Sentiment Predictions at Runtime

Sentiment analysis (SA) systems, though widely applied in many domains, ...

Please sign up or login with your details

Forgot password? Click here to reset