Problems and Mitigation Strategies for Developing and Validating Statistical Cyber Defenses

Abstract

The development and validation of advanced cyber security technology frequently relies on data capturing normal and suspicious activities at various system layers. However, getting access to meaningful data continues to be a major hurdle for innovation in statistical cyber defense research. This paper describes the data challenges encountered during development of the machine learning approach called Behavior-Based Access Control (BBAC), together with mitigation strategies that were instrumental in allowing R&D to proceed. The paper also discusses results from applying a spiral-based agile development process focused on continuous experimental validation of the resulting prototype capabilities.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 2014
Accession Number
ADA600800

Entities

People

  • Aaron Adler
  • Michael Atighetchi
  • Michael J. Mayhew
  • Rachel Greenstadt

Organizations

  • RTX

Tags

Communities of Interest

  • Cyber

DTIC Thesaurus Topics

  • Agile Software Development
  • Air Force Research Laboratories
  • Artificial Intelligence
  • Computer Access Control
  • Computer Languages
  • Computer Science
  • Cyber Defense Techniques
  • Cybersecurity
  • Data Sets
  • Electronic Mail
  • Information Science
  • Intrusion Detectors
  • Machine Learning
  • Network Science
  • Prototypes
  • Security
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Cybersecurity.
  • Regression Analysis.
  • Systems Analysis and Design

Technology Areas

  • AI & ML
  • AI & ML - DoD AI Strategy
  • Cyber