Exécution de notre outil de synthèse sur un nouvel article

Résumé : We present a stochastic approach for estimating the robustness of machine learning components in safety-critical systems using perturbation-based testing, and how to use random sampling of the perturbation parameters to get estimates of system performance across the full range of parameter space. This empirical robustness estimation approach enables Test and Evaluation/Verification and Validation of AI enabled systems in high integrity applications. We demonstrate this approach on an open dataset and show that the approach produces results that are equivalent to substantially more involved testing.