Accession Number:

ADA439768

Title:

On-Line Detection of Distributed Attacks from Space-Time Network Flow Patterns

Descriptive Note:

Technical rept.

Corporate Author:

MARYLAND UNIV COLLEGE PARK DEPT OF ELECTRICAL AND COMPUTER ENGINEERING

Personal Author(s):

• Baras, J. S.
• Cardenas, A. A.
• Ramezani, V.

Report Date:

2003-01-01

Pagination or Media Count:

10.0

Abstract:

Parametric and non-parametric change detection algorithms are applied to the problem of detecting changes in the direction of traffic flow. The directionality of the change in a network flow is assumed to have an objective or target. The particular problem of detecting distributed denial of service attacks from distributed observations is presented as a working framework. The performance of our change detection algorithms is evaluated via simulations.

Descriptors:

• *ALGORITHMS
• *DETECTION
• *ONLINE SYSTEMS
• *NETWORK FLOWS
• SIMULATION
• MODELS
• PARAMETERS
• WIRELESS LINKS
• GRAPHS
• TARGETS
• IDENTIFICATION
• CLASSIFICATION
• TRADE OFF ANALYSIS

Subject Categories:

• Numerical Mathematics
• Navigation and Guidance

Distribution Statement:

APPROVED FOR PUBLIC RELEASE