A team of students led by members of the Duke IT Security Office will develop machine learning features that can be used to identify previously unknown web attacks. Attacks targetting websites and web applications are continuous across the internet and protecting Duke's web infrastructure is part of the IT Security Office's mission. The team will have a large dataset of logs from web traffic to explore possible features and evaluate their usefulness for identifiying new types of web attacks. The results from this project may be incorporated into Duke's IT security infrastructure to help protect Duke's network in the future.
Project Lead: Eric Hope