?
Количественные параметры оценки уровня информационной безопасности финансовых организаций
Information security risk event can be interpreted as bank losses associated with imperfect
security systems: vulnerability to DDoS attacks, virus infections, imperfection of fraud
monitoring systems. The draft regulation of the Central Bank of the Russian Federation on the
operational risk management system in a credit institution and a banking group involves taking
into account the component of this risk in calculating the amount of capital to cover losses. The
relationship between the quality of fraud monitoring models and the costs associated with
reimbursing these losses, as well as an increase in the amount of capital to cover operational
risks, can be expressed in a matrix of errors in the classification of machine learning algorithms.
This article provides a brief overview of the laws and regulations governing the use of anti-fraud
systems and notifying the regulator about events of the corresponding risk. Existing high-level
metrics for managing and quantifying the risk of cyber fraud are considered. The obvious
shortcomings of these metrics are pointed out and examples are provided to indicate that they
cannot be misunderstood by organizations. It is proposed to introduce a new indicator that
corrects these quantitative parameters of the assessment.