Security in the Age of AI
In this talk, I will discuss three major efforts at Northwestern’s Security & AI Lab (NSAIL). First, I will discuss NCEWS (Northwestern Cyber Early Warning System). Given a CVE v, NCEWS predicts if v will be used in a real-world exploit in the next T units of time (for different T‘s) as well as the severity of v. Next, I will talk about a statistical study on phishing in the age of Generative AI. We ask the question: what (hc,pc) pairs are most susceptible to click on a post where hc refers to human characteristics and pc refers to post characteristics. We analyze hundreds of hypotheses and discover which pairs are susceptible to clicking on potentially malicious posts. Finally, I will discuss our GLAMP system. GLAMP automatically generates variants of know Android malware and then uses the generated malware to train better detection algorithms. All of these efforts were jointly done with a team of students, postdocs, and colleagues, both at Northwestern and elsewhere.
V. S. Subrahmanian
is the Walter P. Murphy Professor of Computer Science at the McCormick School of Engineering, Northwestern University and Buffett Faculty Fellow at the Northwestern Roberta Buffett Institute for Global Affairs. He is also the head of the Northwestern Security and AI Laboratory (NSAIL). Prior to this, he was The Dartmouth College Distinguished Professor in Cybersecurity, Technology, and Society at Dartmouth College, and tenured Professor in the University of Maryland’s Computer Science Department, and Director of the University of Maryland’s Institute for Advanced Computer Studies. His work stands at\\ the intersection of data-driven AI for increased security, policy, and business needs. His keynote speech will be on AI and security problems.