This presentation discusses the definition and value of Cybersec Data Science (CSDS) and why it is more than threat intelligence and risk analysis. We'll look at nine main types of CSDS work and how organizations leverage CSDS in the public sector, finance and health industries and marketing. We'll key in on actionable outcomes and dealing with dirty or half-relevant data.
Additionally, we'll discuss how to clean, cross-reference, and bucketize security data, as well as use machine learning, statistical models and data-pivots to construct metrics. From there, we'll demonstrate how to communicate findings and more.
Have a clear understanding of Cybersec Data Science and how can it be used in a variety of organizations and missions. Specific tasks and operational examples will be provided, such as how large financials integrate it into adversary assimilation and real-world risk decision support.
Learn effective techniques derived from Cybersec Data Science practices such as cross-referencing internal metrics with industry norms, tracing cybercrime monetization strategies, attack flow modeling, conducting results-driven analysis, and prioritizing control efforts. Tips will also be given on clearly communicating findings to executives.
Explain how can become a cybersecurity data scientist (or hire a good one), which skills are necessary (and how to learn them), what goes into building an effective team (and where the team should sit within an organization), and the proper mindset and mission of the team.