What is a data scientist and how is the cyber domain connected?
The data scientist is a combination of a programmer, statistician, and a domain expert. This combination of skills, knowledge, and expertise allows the data scientist to use Artificial Intelligence techniques (and mostly machine learning) to solve problems in his domain.
Cyber Data scientist’s goal is to solve problems from the cybersecurity domain using machine learning algorithms.
The Fundamental keys :
- Cyber domain expertise: understand how cyberspace works, what the cyber-attack lifecycle is, and how cyber/information security measures treat them.
- Statistics, AI & ML knowledge: master statistic and machine learning in order to find the most suitable way to model the problem.
- Tools & Coding Skills: the entire process of data gathering processing, analytics, evaluation, and deployment is performed by code or by other technical tools.
Having a basic understanding of these fundamentals will ease your way to throw the next more practical modules, below I present how the 4-level diagram of solving a cyber problem using ML is integrated with the fundamentals, bottom line no fundamental – no solutions!
4-level modeling diagram
- Problem – the cyber threat we are dealing with (= cyber domain expertise)
- Task – problem representation (= machine learning)
- Model –model to solve the task (= tools)
- Algorithm – algorithm that builds our model