ECE SEMINAR: Nowhere to Run, Nowhere to Hide: The Use of a Cognitive Biometric to Establish Identity in Cyberspace

Mar 11

This event has passed.

Friday, March 11, 2022 - 12:00pm to 1:00pm

Damon Woodard

Presenter

Damon Woodard

Abstract

Society relies on the internet for both commerce and trusted communication. To thwart future cyber and national security threats, a reliable means of establishing those in cyberspace is critically important. The use of physiological-based biometrics such as face, iris, and fingerprints is accepted as an irrefutable means of establishing identity in the physical world. Unfortunately, their use in cyberspace is extremely limited. It is estimated that the internet is comprised of 70% - 80% textual data, providing a rich source of information for establishing an online identity. This seminar discusses using a cognitive biometric modality, namely online text, to establish identity in cyberspace. The challenges of this identification method, artificial intelligence-enabled authorship attribution, are briefly presented. The presentation continues with a discussion of our recent advances in authorship attribution methods based upon natural language processing (NLP) and text analytics, allowing for nearly a 90% correct identification rate involving over 27,000 individuals. A discussion of future research directions in related work is given to conclude the presentation.

Biography

Dr. Woodard currently serves as the Director of AI Partnerships for the University of Florida’s Artificial Intelligence Initiative. He is currently an Associate Professor within the Electrical and Computer Engineering Department at the University of Florida. He is also a member of the Florida Institute for Cybersecurity (FICS) Research. Dr. Woodard is an IEEE Senior Member, an ACM Senior Member, a National Academy of Science Kavli Frontiers Fellow, and a member of the Association for the Advancement of Artificial Intelligence (AAAI). He received his Ph.D. in Computer Science and Engineering from the University of Notre Dame, his M.E. in Computer Science and Engineering from Penn State University, and his B.S. in Computer Science and Computer Information Systems from Tulane University.

Before becoming a faculty member, Dr. Woodard was a Director of Central Intelligence postdoctoral fellow. His research interests include cybersecurity, biometrics/identity science, artificial intelligence, applied machine learning, computer vision, and natural language processing. His current research projects include authorship attribution (stylometry) / computational behavioral analytics via text analytics and natural language processing, image analysis/machine learning-based hardware assurance (hardware trojan detection, PCB bill of materials), and adversarial machine learning (DeepFake detection).

Zoom Link:

https://duke.zoom.us/j/96113083714?pwd=SEpZSTJrN2FLUmxYTjZzM0lIV1dOZz09

Passcode: 

789550