ThreatPredict: From Global Social and Technical Big Data to Cyber Threat Forecast

摘要

Predicting the next threats that may occurs in the Internet is a multi-faceted problem as the predictions must be enough precise and given as most as possible in advance to be exploited efficiently, for example to setup defensive measures. The ThreatPredict project aims at building predictive models by integrating exogenous sources of data using machine learning algorithms. This paper reports the most notable results using technical data from security sensors or contextual information about darkweb cyber-criminal markets and data breaches.