Evaluating Trade-offs in Computer Vision Between Attribute Privacy, Fairness and Utility
It addresses privacy and fairness trade-offs in computer vision, which is incremental as it builds on existing adversarial methods.
The paper investigates trade-offs between utility, fairness, and attribute privacy in computer vision, finding that these interactions are more complex and nonlinear than expected.
This paper investigates to what degree and magnitude tradeoffs exist between utility, fairness and attribute privacy in computer vision. Regarding privacy, we look at this important problem specifically in the context of attribute inference attacks, a less addressed form of privacy. To create a variety of models with different preferences, we use adversarial methods to intervene on attributes relating to fairness and privacy. We see that that certain tradeoffs exist between fairness and utility, privacy and utility, and between privacy and fairness. The results also show that those tradeoffs and interactions are more complex and nonlinear between the three goals than intuition would suggest.