Optimized security analytics

Security analytics systems use big data frameworks (e.g. Hadoop and Spark) for analysing security event data to detect cyber-attacks.

The available big data frameworks use different configuration parameters and machine learning (ML) algorithms for optimising cybersecurity analytical solutions. It is important to implement and understand the machine learning (ML) algorithms and optimisation mechanisms underpinning the well-known big data frameworks like Hadoop and Spark. 

This project investigates the impact of Spark Configuration parameters on the response time of a security analytics system, while using different ML algorithms. The project also implements a set of algorithms for optimising solutions for security analytics.

Theme
Securing our future

Booth
SF21

School
Computer Science

Exhibitor
Jacob Correll

vote for this project: sF21

Back to project list