Study level

  • PhD
  • Master of Philosophy

Faculty/School

Faculty of Science

School of Computer Science

Topic status

We're looking for students to study this topic.

Research centre

Supervisors

Dr Yi Lu
Position
Senior Lecturer in Cybersecurity
Division / Faculty
Faculty of Science

External supervisors

  • Dr Huaming Chen, University of Sydney

Overview

Software vulnerability is a major threat to the security of software systems. Thus, the successful prediction of security vulnerability is one of the most effective attack mitigation solutions. Existing approaches for software vulnerability detection (SVD) can be classified into static and dynamic methods. Powered by AI capabilities, especially with the advancement of machine learning techniques, current software has been produced with more sophisticated methodologies and components. This has made the automatic vulnerability proneness prediction even more challenging. Recent research efforts have demonstrated some game changers from feature representations, graph neural network and deep learning model design such as including more semantic meaning and deep-learnt features from code.

Research activities

In this project, we will conduct cutting-edge research by leveraging deep learning techniques for fine-grained vulnerability detection and investigate the performance of different feature representations, GNN&DL models, for vulnerability detection. In details, the project will:

  • perform systematic analysis of various feature representation methods to represent the source code semantics and dynamics.
  • develop state-of-the-art deep learning model to identify software vulnerability in fine-grained level.

You will be expected to work with Dr. Yi Lu (QUT) and Dr. Huaming Chen (USYD) for this project.

Outcomes

Given some specific goals for this project, we expect you to:

  • complete the systematic evaluation of the overall framework for SVD task
  • develop a novel full-supervised model for SVD task.

Skills and experience

To be considered for this project, we expect you to have:

  • knowledge of data mining and machine learning
  • knowledge of software analysis, such as static software analysis
  • good programming skills.

Scholarships

You may be eligible to apply for a research scholarship.

Explore our research scholarships

Keywords

Contact

Contact the supervisor for more information.