The Challenges of Leveraging Threat Intelligence to Stop Data Breaches

Abstract

Data breaches and security incidents are becoming increasingly costly and statistics show that hackers are highly motivated to acquire confidential data as the financial benefits are substantial. Hence, business data has become a top priority to be compromised. Threat Intelligence has been recently introduced by organisations as a means to gain greater visibility of cyber threats, especially data breaches, in order to better protect their digital assets. A well-planned implementation of threat intelligence enables organisations to predict and (at least partially) prevent cyber crime, such as data breaches or data exfilteration ({\ie} attempts to move data outside an organization’s secure perimeters). This allows an organisation to better understand different aspects of threats, including identifying the adversary and how and why they intend to compromise digital assets, consequences of attacks, which assets can be compromised, to what level and how to detect threats, how to respond to them. A key enabler to implement threat intelligence is to build sophisticated data-driven architectures using machine learning that allows an organisation's cyber data (stored in different silos throughout an organisation's digital infrastructure) to be managed effectively. However, one of the biggest challenges of machine learning in cybersecurity is to enable an efficient implementation that scales in today's complex threat landscapes and digital infrastructure, respectively. In this paper, we review the data breaches problem and discuss the challenges of implementing machine learning to mitigate security threats and data intelligence to predict cyber threats that could potentially lead to data breaches leakage. Then illustrate how the future of effective threat intelligence is closely linked to efficiently applying machine learning approaches in this field, and outline future research directions in this area