Predicting cyber attacks with bayesian networks using unconventional signals

摘要: The ability to predict cyber incidents before they occur will help mitigate malicious activities and their impact. This is a challenging task departure from intrusion detection where observables of are analyzed. Since there no direct observable the incident actually happens, predictive analysis need be based on non-conventional signals that may or not directly related potential victim entity. paper presents our preliminary findings through use Bayesian classifier process drawn global events social media. results show promising prediction performance for an anonymized organization even though specific organization.