
This paper introduces VRCP, a novel framework that leverages conformal prediction and neural network verification to construct prediction sets that maintain coverage guarantees for machine learning models, even in the presence of adversarial attacks.


coremsg

verifiably-robust-conformal-prediction-for-improved-uncertainty-quantification-under-adversarial-attacks


Verifiably Robust Conformal Prediction for Improved Uncertainty Quantification Under Adversarial Attacks
