Machine Learning for Cyber Security
Our daily life, economic vitality, and national security depend on a stable, safe, and resilient cyberspace. A safe and secure cyberspace is a crucial element for a vast array of networks in order to facilitate communication, travel, powering of homes, running of economy, and provision of government services. Unfortunately, cyber intrusions and attacks have increased dramatically over the last decade, exposing sensitive personal and business information, disrupting critical operations, and imposing high costs and risks on the economy as well as other aspects of everyday life. Cyber Security is the intersection of computer security network security and information security and is a domain problem, rather than a domain solution, thus, it seeks solutions from other areas.
Traditionally, security problems were aided by a mathematical model, e.g., secrecy or cryptography, however because modern cyber security deals with abstract threats, such as malware detection, intrusion detection, and data leakage, which cannot be solved by mathematical models only, other methods should be applied.
In the lecture I will describe how Machine Learning can be applied to solve cyber security problems. I will give a brief review of the concept of Machine Learning followed by a description of two cyber security related projects to which machine learning was applied for cyber security challenges. One project aimed to discover malware by identifying anomalies in the network behavior of applications and the other aimed at data leakage prevention.
Bracha Shapira is an Associate Professor of Information-Systems Engineering at Ben-Gurion University of the Negev where she serves as the head of the department.
She specialized in profiling and personalization of systems for users based on their automatically inferred interests. She is involved in many research projects in the field of information security, personalization and data mining. The projects are funded by both industry and governmental entities.
She is involved with the Deutsche Telekom laboratory at BGU, where she manages various large research projects in the field of information security and usability. She is also involved in research projects for various governmental entities mainly in the field of information security. The work presented in the seminar is a joint work at the cyber security research center at BGU with Prof Elovici, Prof. Rokach, Lena Tenenbaum and Gilad Katz