Special Topics in Cybersecurity: Machine Learning for Cybersecurity

Catalog description

Cybersecurity has become a high-stakes battlefield, and machine learning is both a weapon and a shield. From home IoT devices to critical infrastructure, the stakes have never been higher: the attack surface of our systems keeps increasing; attackers are more and more determined and sophisticated; and ML is emerging as a tool to automate attacks. This course will explore the most significant uses of ML for cybersecurity over the past four decades while focusing on the most promising defenses proposed in recent years. Example applications that will be covered are malware detection, spam detection, anomaly detection for computer networks, anomaly detection for industrial control systems, generating private synthetic data, vulnerability detection, and assisting in security-relevant decision-making by both security experts and end users. The course will also teach students to think critically about the challenges and pitfalls of applying ML to cybersecurity, such as the base rate fallacy, unavailability of training data, lack of interpretability of ML models, and susceptibility of ML models to adversarial examples.