Automated Software Vulnerability Patching using Dynamic Symbolic Traces

Deep learning (DL) has emerged as a viable means for identifying software bugs and vulnerabilities. The success of DL relies on having a suitable representation of the problem domain. However, existing DL-based solutions for learning program representations have limitations – they either cannot capture the deep, precise program semantics or suffer from poor scalability. We plan to provide a DL system to learn program presentations by combining static source code information and dynamic program execution traces. By collaborating in two diverse multicultural research groups, participating institutions in Canada and United Kingdom will benefit from sharing knowledge and expertise in this cutting-edge field of cybersecurity and software engineering. This collaboration will enhance the reputation of these institutions in the security and software engineering communities, attracting top talent and opportunities. Moreover, participants will have the chance to develop new technical skills and social skills, and learn about the state-of-the-art technological innovations in vulnerability detection.

Faculty Supervisor:

Shin Hwei Tan

Student:

Partner:

University of Leeds

Discipline:

Computer science

Sector:

Education

University:

Concordia University

Program: