Secure Code Generation: Integrating Security into AI-Driven Software Development
Dawn Song, Professor
Electrical Engineering and Computer Science
Applications for Spring 2025 are closed for this project.
The intersection of AI and software security presents unique opportunities and challenges. This project focuses on leveraging artificial intelligence to enhance secure code generation and protect software systems from vulnerabilities.
Key objectives include:
- Secure Code Generation: Developing AI models that can generate code snippets with built-in security best practices, reducing the likelihood of introducing vulnerabilities.
- Automated Vulnerability Detection: Creating AI-driven tools to identify and remediate security flaws in existing codebases.
- Adversarial Testing: Implementing AI techniques to simulate attacks and test the resilience of software systems.
- Secure Development Frameworks: Integrating AI tools into the software development lifecycle to promote secure coding standards and practices.
Role: Participants will work on both the development of AI models for security applications and the integration of these models into practical software development workflows.
Qualifications: - Background in computer science or software engineering with a focus on security.
- Proficient in programming languages such as Python, Rust, C++.
- Experience with machine learning frameworks and security tools.
- Knowledge of software development lifecycle and secure coding practices.
Day-to-day supervisor for this project: Jingxuan He
Hours: 12 or more hours
Engineering, Design & Technologies