PrintPrint

Awards

Topic Information Award/Contract Number Proposal Information Company Performance
Period
Award/Contract
Value
Abstract

H-SB04.2-001
Cross-Domain Attack Correlation Technologies

NBCHC050003 0421012
(FY04.2 Phase I)
Cross-Domain Intrusion Detection using Privacy-Preserving Distributed Data Mining Technologies

AGNIK, LLC
8840 Stanford Blvd. STE 1300
Columbia, MD 21045-5833

11/01/2004
to
05/15/2005
$99,995.00

This document proposes development of PURSUIT, a cross-domain intrusion detection system that relies upon state-of-the-art privacy-preserving distributed data-mining (PPDM) technology. PURSUIT has a distributed multi-agent architecture that supports formation of ad-hoc peer-to-peer, hierarchical, and other collaborative coalitions with due attention to the security and privacy issues. It will be equipped with PPDM algorithms so that the patterns can be computed and shared across the sites without sharing the privacy-sensitive data. The algorithmic foundation of the approach is based on combination of secured multi-party computation and randomized transformation techniques that allow sharing of attack patterns not the raw data. This research will be performed by Agnik, Tresys, and University of Minnesota (UNM) Army High Performance Computing research Center. Agnik team has a strong track record in distributed and privacy preserving data mining. Tresys is a security company with strong record in working with several major governmental agencies dealing with national security. The UMN team has a strong record in building intrusion detection systems, including the MINDS IDS that is currently being deployed in more than sixty different army locations. Being a plug-in IDS PURSUIT has the commercial potential to be marketed to all organizations that currently use one or more IDS.

H-SB04.2-001
Cross-Domain Attack Correlation Technologies

NBCHC050143 0422002
(FY04.2 Phase II)
Cross-Domain Intrusion Detection using Privacy-Preserving Distributed Data Mining Technologies

AGNIK, LLC
8840 Stanford Blvd. STE 1300
Columbia, MD 21045-5833

11/01/2005
to
04/30/2008
$749,999.00

This proposal proposes development of PURSUIT, a cross-domain intrusion detection and prevention system that relies upon state-of-the-art privacy-preserving distributed data mining (PPDM) technology. PURSUIT has a distributed multi-agent architecture that supports formation of ad-hoc collaborative coalitions with due attention to security and privacy issues. PURSUIT's foundation is based on different PPDM techniques such as k-ring of privacy, secured multi-party computation, and randomized transformations that allow privacy-sensitive sharing of attack patterns, not the raw data. This project will be performed by Agnik, Tresys, and University of Minnesota Army High Performance Computing research Center. The Agnik team has a strong track record in distributed and privacy preserving data mining. Tresys is a security company with strong record in working with many governmental agencies dealing with national security. The UMN team has a strong record in building intrusion detection systems, including the MINDS system. Since the PURSUIT links up available intrusion detection and prevention systems, it has the commercial potential to be marketed to all organizations that currently use such systems. An early PURSUIT coalition has already been set up and it includes organizations such as University of Illinois, SRI International, Purdue University, Ohio State University, and Stevens Institute of Technology.

H-SB04.2-005
Innovative Techniques for Concealed Weapons or Explosive Detection at a Distance

NBCHC050001 0421192
(FY04.2 Phase I)
Electromagnetic Concealed Weapons Detection at a Distance

Pharad, LLC
797 Cromwell Park Drive
Suite V
Glen Burnie, MD 21061-2540

11/01/2004
to
05/15/2005
$100,000.00

Pharad proposes to design a cost effective portable electromagnetic concealed weapons detection system that can be readily installed in a public areas, without interrupting the flow of human traffic. The system uses complex resonances for the identification of known targets, providing significant cost and size benefits over conventional imaging approaches. Our solution will be able to accurately detect and identify concealed weapons, metallic and non-metallic, at distances > 50 meters. Another unique advantage is that weapon detection is independent of the excitation manner. To minimize the size of the electromagnetic weapons identifier sensor we will use millimeter-wave frequencies as the interrogation signals, which also provides greater immunity to interference from other wireless services. In addition, a millimeter-wave based system provides a large available bandwidth that can be used to interrogate the target, increasing the resolution for target recognition. We will also incorporate efficient signal processing algorithms to ensure accurate determination of the presence of a known target.

H-SB04.2-005
Innovative Techniques for Concealed Weapons or Explosive Detection at a Distance

NBCHC060005 0423003
(FY04.2 Phase II)
Electromagnetic Concealed Weapons Detection at a Distance

Pharad, LLC
797 Cromwell Park Drive
Suite V
Glen Burnie, MD 21061-2540

11/15/2005
to
09/13/2007
$750,000.00

In this Phase II project Pharad proposes to develop and fabricate an engineering prototype concealed weapons detection system and test its weapon detection capability in a laboratory demonstration. The prototype system will incorporate the innovative electromagnetic technology for concealed weapons detection that we proposed and validated theoretically and experimentally in Phase I. Having successfully achieved our Phase I goals, our Phase II effort will further the development of the weapons detection system. Our novel technical solution for concealed weapons detection uses millimeter-wave signals to excite resonances in the target, creating a unique signature that can be used to characterize the object. Using such excitation signals, benefits such as increased resolution and reduced component size can be achieved. In addition, the EM signature of the target exhibits more features available for classifying the object. Our proposed Phase II effort comprises a number of hardware and software development activities including the implementation of the target detection algorithm, development of the prototype mm-wave sensor module hardware and software, and the development of the Central Station subsystem. In addition, we will test the prototype system in a laboratory demonstration, and deliver a prototype sensor to HSARPA along with the Central Station software.