Advanced cyber attacks and cyber threats have the power of mutating and outbreaking faster than the response of current detection models that are based on artificial intelligent and Big Data analytics. Digital competitiveness of any organization thus desires high-quality large datasets and their innovative use. This project explores the creation of massive software security datasets and their innovative use.
This project will contribute to the development of a distributed data collection infrastructure. It will include the malware samples and binary-level vulnerabilities. These will cover various types of malware on platforms from mobile devices, personal computers to cloud, including backdoors, worms, shellcode, adware, rootkits, spyware, Trojan horses, viruses, and so on. The vulnerabilities and their exploit code will also be included in the datasets.
A virtualization infrastructure will be constructed to collect high-fidelity data while testing malware and reproducing attacks. The blue and red teaming events, vulnerability analysis and penetration testing will also present in our datasets. Various big data techniques will be studied, benchmarked and adapted to enable real-time data analytics. Early warning detection techniques based on real-time data will be developed.
This is a prestigious PhD scholarship supervised by both UQ and Data61 researchers. We invite anyone who is interested in security analytics to be part of this project as a PhD. The PhD application will follow this process:
- EOI to UQ (see How to Apply)
- Acceptance as preferred candidate and invitation to submit full application to UQ PhD programme
- Acceptance as UQ candidate and interview with UQ and Data61 supervisors
- Application for Data61 scholarships
- Acceptance and commencement of PhD scholarships.
Working with leading researchers from UQ Cyber Security and CSIRO’s Data61, the PhD student will gain access to state-of-the-art equipment through UQ’s cyber security facilities and groups, Data61’s facilities, UQ Energy Testlab, and specific domain expertise through collaboration with other research groups at ITEE.
For more information click "LINK TO ORIGINAL" below.