Supervised machine learning has been successfully used in the past to infer a system's security boundary by training classifiers (also referred to as security rules) on a large number of simulated operating conditions. Although significant research has been carried out on using classifiers for the detection of critical operating points, using classifiers for the subsequent identification of suitable preventive/corrective control actions remains underdeveloped. This paper focuses on addressing the challenges that arise when utilizing security rules for control purposes. The inherent trade-off between operating cost and security risk is explored in detail. To optimally navigate this trade-off, a novel approach is proposed that uses an ensemble learning method (AdaBoost) to infer a probabilistic description of a system's security boundary and Platt Calibration to correct the introduced bias. Subsequently, a general-purpose framework for building probabilistic and disjunctive security rules of a system's secure operating domain is developed that can be embedded within classic operation formulations. Through case studies on the IEEE 39-bus system, it is showcased how security rules can be efficiently utilized to optimally operate the system under multiple uncertainties while respecting a user-defined cost-risk balance. This is a fundamental step towards embedding data-driven models within classic optimisation approaches.