Security Data Science
securitydatascience.org is a member association focused on the advancement of the security data science profession. We are planning many exciting announcements in the near future. Join us for free to receive all announcements.
Security Data Scientist are professionals that specialize in data analytics for security and fraud. They have a broad range of specialties that may include one or more of the following:
Insider threat detection
Computer and network forensics
Governance, risk and compliance
Fraud and loss analytics
Advanced threat mitigation
... and many more
Security Data Science is the application of advanced analytics to activity and access data to uncover unknown risks. Generally Data Science is the practice of deriving valuable insights from data. In Security the valuable insight leads to reduced risk. Data Science is emerging to meet the challenges of processing very large data sets i.e. "Big Data" and the explosion of new data generated from smart devices, web, mobile and social media. Data Science has a long and rich history in security and fraud monitoring. The information security and fraud prevention industry have been evolving Security Data Science in order to tackle the challenges of managing and gaining insights from huge streams of log data, discover insider threats and prevent fraud. Security Data Science is "data driven" meaning that new insights and value comes directly from data.
Manu Sharma said it best in a presentation on Data Science:
This definition not only captures the unique skills needed in a Data Scientist but it also captures the essence of data science. A data scientist is driven by curiosity to explore and experiment with data. Experience in mashing up data from multiple sources helps the Data Scientist develop a keen intuition into what data is relevant to a given set of questions. Experience in cleaning, parsing and deciphering vastly different data types allows the Data Scientist to gather the needed data. Data Scientist understand how to standardize data into intelligible information and then apply statistics, modeling and visualizations in order to draw insights.
Security Data Science is focused on advancing information security through practical applications of exploratory data analysis, statistics, machine learning and data visualization. Although the tools and techniques are no different that those used for data science in any data domain, this group has a micro-focus on reducing risk, identifying fraud or malicious insiders using data science. We believe domain knowledge and experience is critical to successfully applying analytics to reduce risk and fraud losses. We believe developing Security Data Science is needed to bring together several Security & Fraud sub-domains under a combined practice including SIEM development, advanced security metrics, visualization and analytics. Read more on why Security Data Science is needed.