Learning Software Security Analysers with Imperfect Data

该项目旨在系统地研究下一代基于学习的软件安全分析，以检测现实世界中的大型软件中的漏洞。预期的基于学习的基础将支持处理不完善的数据，以便对关键软件组件进行精确、可扩展和自适应的安全分析，从而捕捉现有方法遗漏的重要安全漏洞。该项目的成功将进一步提高澳大利亚在这一重要领域研究的国际竞争力，并将使任何软件系统根深蒂固的澳大利亚行业和企业受益，如交通，智能家居，医疗设备，国防和金融。

This project aims to systematically investigate next-generation learning-based software security analysis to detect vulnerabilities in real-world large-scale software. The expected learning-based foundation will support the handling of imperfect data in order to provide a precise, scalable and adaptive security analysis of the critical software components, thus capturing important security vulnerabilities missed by existing approaches. The success of this project will further enhance the international competitiveness of Australian research in this important field and will benefit any Australian industry and business where software systems are deeply-rooted, such as transportation, smart homes, medical devices, defence and finance.