Multi-Agent System for Resource Reliability

Abstract

In this Phase 1 SBIR research we demonstrated the feasibility of a unique system for maintaining network resource reliability through a decentralized multi-agent architecture by prototyping key features of the system. Our approach differs from other computer security tools in a number of ways. First, our system does not rely on the presence of a central analysis unit. Instead, individual agents monitor individual hosts and/or local portions of the network, communicating between agents when needed. This design is not only easily scalable, it enables the agents to perform local responses, even when much of the network is compromised. Second, unlike many intrusion detection programs which have hard coded responses to known attacks, our system can respond to both known attacks and unexplained anomalies. Third, our agents are able to reconcile differing local view through data fusion, thus enabling the agents to respond to network degrading events with increasing accuracy as information is collected and aggregated from other agents. Phase 1 research and development of a prototype for network resource reliability has laid the groundwork for the Phase 2 implementation of MASRR, a Multi-Agent System for Resource Reliability, and its eventual commercialization.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 20, 1999
Accession Number
ADA371796

Entities

People

  • Tamitha Carpenter

Organizations

  • Stottler Henke Associates

Tags

Communities of Interest

  • Counter WMD
  • Cyber
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Application Protocols
  • Artificial Intelligence
  • Computer Communications
  • Computer Network Security
  • Computer Networks
  • Computers
  • Cybersecurity
  • Detection
  • Heterogeneous Networks
  • Information Science
  • Information Systems
  • Intrusion Detection
  • Local Area Networks
  • Machine Learning
  • Multiagent Systems
  • Network Science
  • Reliability

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Software Engineering
  • Systems Analysis and Design

Technology Areas

  • Cyber