Description

Machine learning (ML) algorithms are increasingly embedded in cybersecurity systems, like spam/malware filters and network intrusion detectors, and safety-critical applications, like autonomous vehicles. These ML systems are vulnerable to attack. For example, a spammer may try to evade a spam filter with a carefully crafted email, or alternatively may try to poison the filters training data with bogus examples rendering the filter useless. In this course, students will learn how to implement ML algorithms, build practical ML systems, perform evasion and poisoning attacks, and defend against such attacks. The course will cover the following ML problems and tools: classification, dimensionality reduction, clustering, regression, and deep neural networks. Grading will be based on biweekly Python programming assignments with written reports.