Synthetic data is often presented as a method for sharing sensitive information in privacy-preserving manner by reproducing the global statistical properties of original without dis closing about any individual. In practice, with other anonymization methods, synthetic cannot entirely eliminate privacy risks. These residual risks need instead to be ex-post uncovered and assessed. However, quanti...

Integration of Uncrewed Aircraft into unsegregated airspace requires robust and objective risk assessment in order to prevent exposure existing users additional risk. A probabilistic Mid-Air Collision model is developed based on surveillance traffic data for the intended operational area. Simulated probable scenarios are superimposed a desired operation then sampled using Monte Carlo methods. T...

We focus on two particular aspects of model risk: the inability a chosen to fit observed market prices at given point in time (calibration error) and risk due recalibration parameters (in contradiction assumptions). In this context, we use relative entropy as pre-metric order quantify these sources common framework, consider trade-offs between them when choosing frequency with which recalibrate...