Restricted Research - Award List, Note/Discussion Page

Fiscal Year: 2021

168  University of North Texas  (84464)

Principal Investigator: Ding,Junhua

Total Amount of Contract, Award, or Gift (Annual before 2011): $ 49,625

Exceeds $250,000 (Is it flagged?): No

Start and End Dates: - 9/17/21

Restricted Research: YES

Academic Discipline: Information Science

Department, Center, School, or Institute: College of Information

Title of Contract, Award, or Gift: 2020 Tuskegee University NCAEC Research Grant

Name of Granting or Contracting Agency/Entity: Tuskegee University

CFDA: 12.000

Program Title: N/A

Note:

The research team at Tuskegee University (TU) (a CAE-CD and minority institution) proposes to develop a framework for improving the effectiveness of anomaly intrusion detection for web applications in partnership with University of North Texas (UNT) (a CAE-CR institution) using current big data and machine learning techniques. %Cyber-attacks through web applications cut across private businesses, industries, government organizations, and military establishments. Intrusion detection is a widely adopted solution for protecting systems from cyber-attacks. Intrusion detection is a widely adopted solution for protecting systems from cyber-attacks, which are rampant across public and private sectors. However, none of the current Intrusion Detection Systems (IDSs) is effective in preventing most attacks on cybersecurity systems. Recent advances in machine learning, especially deep learning, provide an unprecedented opportunity for building highly effective IDSs. The overarching goal of this project is to investigate big data and machine learning driven approaches for improving the effectiveness and performance of anomaly intrusion detection for web applications. The framework to be developed includes strategies for collecting, labeling, enhancing, and augmenting the data for analytics, solutions for data representation, feature learning and classification of system behaviors, and an implementation of the framework to realize an IDS. We expect the new techniques to help achieve the highest accuracy in anomaly intrusion detection and the lowest false-positive rate, compared to existing techniques. The other important goal of this project is to enhance the research potential of TU, which is a Historically Black College and University (HBCU) and to encourage minorities to pursue PhD in data science and cybersecurity areas.

Discussion: No discussion notes

 

Close Window