A machine learning framework for gathering and leveraging web data to Cyber-Threat lntelligence

Author nameParis Koloveas
TitleA machine learning framework for gathering and leveraging web data to Cyber-Threat lntelligence
Year2019-2020
Supervisor

Christos Tryfonopoulos

ChristosTryfonopoulos

Summary

In this day and age, technology has become more accessible than ever and is deeply ingrained in society. A plethora of different devices and platforms, ranging from company servers and commodity PCs to mobile phones and wearables, interconnect a wide range of stakeholders such as households, organisations and critical infrastructures. The sheer volume and variety of the different operating systems, the device particularities, the various usage domains and the accessibility-ready nature of the platforms, creates a vast and complex threat landscape that is difficult to contain. Staying on top of these evolving cyber-threats has become an increasingly difficult task that nowadays relies heavily on collecting and utilising Cyber-Threat Intelligence to prevent attacks, a task that entails the collection, analysis, leveraging and sharing of huge volumes of data. In this thesis, we present our work for the creation of inTIME [1], an AI-driven framework that provides an all-encompassing view in the Cyber-Threat Intelligence process and allows security analysts to easily identify, collect, analyse, extract, integrate and share CTI data in order to efficiently tackle the task of securing internet-connected smart devices at scale.