| NSF Org: |
OAC Office of Advanced Cyberinfrastructure (OAC) |
| Recipient: |
|
| Initial Amendment Date: | August 31, 2015 |
| Latest Amendment Date: | August 31, 2015 |
| Award Number: | 1547390 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Rob Beverly
OAC Office of Advanced Cyberinfrastructure (OAC) CSE Directorate for Computer and Information Science and Engineering |
| Start Date: | January 1, 2016 |
| End Date: | December 31, 2018 (Estimated) |
| Total Intended Award Amount: | $139,831.00 |
| Total Awarded Amount to Date: | $139,831.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
2550 NORTHWESTERN AVE # 1100 WEST LAFAYETTE IN US 47906-1332 (765)494-1055 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
301 N. University Street West Lafayette IN US 47907-2107 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | Cybersecurity Innovation |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.070 |
ABSTRACT
Collaborative, multi-disciplinary and multi-institutional research projects require secure and resilient cyberinfrastructure in order to efficiently support data sharing, access to remote scientific instruments, video-conferencing and on-line discussions. The underlying network plays a crucial role in supporting these needs in that it must provide assurance about the security of data and collaborative activities. This project addresses such requirement by designing and developing a network architecture to securely share data among groups of scientists. A community of scientists sharing a common interest and supporting resources is called a mission. This project will design and prototype the architecture of the Assured Mission Delivery Network (AMDN), which will enable collaboration among scientific communities involving multiple independent organizations with varying levels of trust.
They novelty of AMDN lies in the notion of network-level Mission Assurance Services (MAS); these services allows mission directors to specify actions to be taken by the network to deal with attacks and anomalies and to quickly reconfigure the network to best assure the successful completion of the mission. Security is the key part of the AMDN design, and addresses essential functionality such as authentication, integrity, accountability and privacy. AMDN also includes Collective Anomaly Detection, in which intra- and inter-cloud networking alarms and anomalies indicative of attacks are combined and used for mission assurance strategies. The detected anomalies and alarms are correlated over the whole system in order to detect sophisticated attacks that might be undetectable at the single node level. The security of the entire system is flexible and programmable depending on the nature of collaborations, computing resources needed, and various requirements of scientists. In addition to scientific use, AMDN can be used for commercial applications such as financial data sharing among banks or health data sharing among hospitals and between critical infrastructures such as Smart Grids. Although AMDN is primarily designed for wide-area network usage, it can be used for services and clients residing inside a single cloud or data center.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Collaborative, multi-disciplinary and multi-institutional research projects require secure and resilient cyberinfrastructure in order to efficiently support data sharing, access to remote scientific instruments, video-conferencing and on-line discussions. The underlying network plays a crucial role in supporting these needs in that it must provide assurance about the security of data and collaborative activities. This project has addressed such requirement by designing and developing a network architecture to securely share data among groups of scientists. A community of scientists sharing a common interest and supporting resources is called a mission. This project has investigated security techniques to enhance the network architecture.
The first key outcome is related to the development of a protocols for securerly transmitt and manage the network rules. Such rules allow users to specify tpolicies that the system must comply with when routing data packets across the network. Such data packets contain scientific data or other data of interest that collaborating institutions need to exchange.
The second key outcome is related to the use of deep neural networks for various security tasks, such intrusion detection. Intrusion detection is a key security technique widely used to protect infrastructure. However, training the detection models to identify new attacks reliably requires a large amount of new labeled training data which is often expensive and time-consuming to collect. In this work we have investigated the viability of transfer learning, which enables transferring learned features and knowledge from a trained source model to a target model with minimal new training data, for security applications. Our experimental results show that transfer learning is effective in reducing the size of the newly required training datasets while at the same time obtaining high accuracy.
Last Modified: 02/05/2019
Modified by: Elisa Bertino
Please report errors in award information by writing to: awardsearch@nsf.gov.
