Broad Scale Situational Awareness: Monitoring the State of the Nation s Networks through Social Media
Abstract
This proposal will create a broad-scale detection system for nationwide network attacks by leveraging social media. The will attempt on overcoming the natural language processing barrier for informal language used in social media by using both supervised and semi supervised machine learning, capturing references and associating them (identifying) to physical network within social media, and dealing with scalability problem. Objective: This proposal will create a broad-scale detection system for nationwide network attacks by leveraging social media It will generate a near-real-time map of the nation’s critical network infrastructure, and provide alerts and reports of new and developing network attacks. Approach: This proposal will use advances in the fields of natural language processing and machine learning will be used to interpret informal comments about network trouble from millions of online users, and map the interpretation to (1) specific public and private networks, and (2) the type of network attack Overall Merit and ONR Mission/Relevance: Using natural language processing (NLP) proposed research will provide a more grounded analysis and specific event detection on social media relative to the currently popular but much less grounded elementary statistical (keyword counting) methods of current big-data analytic. More precise and grounded networks attack detection will enhance the robustness and resiliency of Navy networking infrastructure
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 12, 2016
- Source ID
- N000141512232
Entities
People
- James Oates
Organizations
- Office of Naval Research
- United States Navy
- University of Maryland, Baltimore