Data Science or Data Pseudo-Science? Applying Data Science Concepts to Infosec without a PhD

Presented at BSidesLV 2016, Aug. 2, 2016, 11 a.m. (55 minutes).

Looking to learn how to apply fuzzy linear Bayesian regression entropy clustering to your security analyst toolbox? Then this talk is not for you. The goal of this presentation is to demystify and de-bullshit the world of data science for us mere security mortals. I will explain key concepts behind buzzwords such as machine learning, k-means, Bayesian Probability, Lambda Architecture and how they apply to real world security use cases. The presentation will cover how analysts can get started using data science concepts without a PhD and using data they are already collecting in their environment to gain insight into previously unseen threats.

Presenters:

• Ken Westin
  Ken is a creative technologist with 16 years experience building and breaking things through the use/misuse of technology. His technology exploits and endeavors have been featured in Forbes, Good Morning America, Dateline, New York Times, The Economist and others. He has presented at DEF CON, RSA, Black Hat and BSides around the country and other conferences. In the past he developed forensic and data mining tools to aid in the unveiling of various crimes including organized crime rings, tracking stolen property and others.

Links:

• https://bsideslv2016.sched.com/event/7Vgs/data-science-or-data-pseudo-science-applying-data-science-concepts-to-infosec-without-a-phd
• https://www.youtube.com/watch?v=1CQWJDfyQu0

Similar Presentations:

• Black Hat USA 2015 / Why Security Data Science Matters and How It's Different: Pitfalls and Promises of Data Science Based Breach Detection and Threat Intelligence
• BSidesLV 2019 / Security data science -- Getting the fundamentals right
• DeepSec 2019 „Internet of Facts and Fears“ / What Has Data Science Got To Do With It?