Improving Software Fuzzing with AI and ML

What if we could achieve completely ‘contactless’ software security scanning? As the lines between physical and digital security become blurrier and blurrier, software quality standards and testing methodologies must continue to keep pace. Software fuzzing has long been a trusted method for finding vulnerabilities that are difficult to discover using traditional methods.

The application of AI and ML to this field has already begun to bear very promising results. By leveraging deep learning techniques to improve our input corpus and better understand our program's states, we can shine areas on the code logic that would be hidden by approaches like vulnerability scanning and static code analysis, and even traditional software fuzzing.

About Justin Reock

Justin Reock is the Deputy CTO of DX (getdx.com), and is an engineer, speaker, writer, and software practice evangelist with over 20 years of experience working in various software roles. He is an outspoken thought leader, delivering enterprise solutions, numerous keynotes, technical leadership, various publications and community education on developer experience and productivity.

More About Justin »