Project
Safe adoption of machine learning in cybersecurity applications
Over the past few years, the number as well as the sophistication of security threats has been increasing. State-of-the-art security analytics solutions are therefore increasingly depending on machine learning methods to distinguish malicious from normal behavior in diverse contexts. However, with the use of machine learning for security applications on the rise, so are the attacks of cyber- criminals on these methods. Furthermore, there is no set of best practices on how to reduce the attack surface of machine learning methods. This PhD project will investigate the secure adoption of machine learning techniques, and will research, develop and evaluate solutions - including but not limited to middleware - for a variety of cyber-security application cases.