Adversarial Machine Learning

AI and Cybersecurity

MET CS 787 (4 credits)

Prerequisite: MET CS 677 or consent of instructor. Explore the critical intersection between Artificial Intelligence (AI) and cybersecurity, focusing on two interconnected themes: protecting AI systems from vulnerabilities and harnessing the power of AI to address cybersecurity challenges. As AI becomes a cornerstone of modern technology, ensuring the security of AI-powered systems against adversarial attacks, backdoor threats, and model theft is essential. Simultaneously, AI offers transformative capabilities for malware detection, intrusion prevention, and malware analysis. Through a blend of theoretical foundations, hands-on exercises, and real-world case studies, you will study topics such as adversarial machine learning, backdoor injection and defense, intellectual property (IP) protection, and privacy-preserving AI. You will also learn how to design and implement AI-driven tools to identify and mitigate cyber threats in dynamic environments. Practical applications emphasize building resilient AI systems and utilizing advanced AI techniques to enhance security and detect emerging threats. Hands-on labs using existing tools will also be provided and required.

2025FALLMETCS787A1, Sep 2nd to Dec 10th 2025