Data Analytics for Cybersecurity

Erscheinungsjahr 2022
ISBN: 978-1-108-41527-9
Verlag: Cambridge University Press

Buch, Englisch, 240 Seiten, Format (B × H): 157 mm x 235 mm, Gewicht: 459 g

As the world becomes increasingly connected, it is also more exposed to a myriad of cyber threats. We need to use multiple types of tools and techniques to learn and understand the evolving threat landscape. Data is a common thread linking various types of devices and end users. Analyzing data across different segments of cybersecurity domains, particularly data generated during cyber-attacks, can help us understand threats better, prevent future cyber-attacks, and provide insights into the evolving cyber threat landscape. This book takes a data oriented approach to studying cyber threats, showing in depth how traditional methods such as anomaly detection can be extended using data analytics and also applies data analytics to non-traditional views of cybersecurity, such as multi domain analysis, time series and spatial data analysis, and human-centered cybersecurity.

Autoren/Hrsg.

Janeja, Vandana P.

Fachgebiete

• Mathematik | Informatik EDV | Informatik Technische Informatik Computersicherheit
• Mathematik | Informatik EDV | Informatik Daten / Datenbanken Data Mining

Inhaltsverzeichnis

Preface; 1. Introduction; 2. Understanding sources of cybersecurity data; 3. Introduction to data mining: clustering, classification and association rule mining; 4. Big data analytics and its need for cybersecurity: advanced DM and complex data types from cybersecurity perspective; 5. Types of Cyber Attacks; 6. Anomaly Detection for cyber security; 7. Anomaly Detection; 8. Cybersecurity through Time Series and Spatial data; 9. Cybersecurity through Network and Graph Data; 10. Human Centered Data Analytics for Cyber security; 11. Future directions in Data Analytics for Cybersecurity; References; Index;

Über Autor(innen)

Janeja, Vandana P.
Vandana Janeja is Professor and Chair of the Information Systems department at the University of Maryland, Baltimore County. Most recently, she also served as an expert at the National Science Foundation supporting data science activities in the Directorate for Computer and Information Science and Engineering (CISE) (2018-2021). Her research interests include discovering knowledge in presence of data heterogeneity. Her research projects include anomaly detection in network communication data, human behavior analytics in heterogeneous device environments, geo spatial context for IP reputation scoring, spatio-temporal analysis across heterogeneous data, ethical thinking in data science. She has been funded through state, federal and private organizations.