[MS/PhD] Seminar Announcement: Dipankar Dasgupta, University of Memphis, Tues May 6, 11am, EEB 132

The following announcement is from Dr. Viktor Prasanna (ECE). Please contact them directly if you have any questions.

Generic LLMs in Cybersecurity

Dipankar Dasgupta

William Hill Professor in Cybersecurity

Director, Center for Information Assurance (CfIA)

University of Memphis

Tuesday, May 6, 2025 | 11am-12pm | EEB 132

Abstract: Generic Large Language Models (GLLMs) are continuously being released with increased size and capabilities, promoting the abilities of these tools as universal problem solvers.  While the reliability of GLLMs’ responses is questionable in many situations, these are augmented/ retrofitted with external resources for different applications including cybersecurity.

The talk will discuss major security concerns of these pre-trained models: first GLLMs are prone to adversarial manipulation such as model poisoning, reverse engineering and side-channel cyberattacks. Second, the security issues related to LLM-generated codes using open-source libraries/codelets for software development can involve software supply chain attacks. These may result in information disclosure, access to restricted resources, privilege escalation, and complete system takeover.

This talk will also cover the benefits and risks of using GLLMs in cybersecurity, particularly, in malware detection, log analysis, intrusion detection, etc. I will highlight the need for diverse AI approaches (non-LLM-based smaller models) trained with application-specific curated data, fine-tuned for well-tested security functionalities in identifying and mitigating emerging cyber threats including zero-day attacks.

Bio:  Dr. Dipankar Dasgupta is a Professor of Computer Science at the University of Memphis since January 1997. He has extensively worked on the applications of bio-inspired and machine learning approaches to cyber defense. His groundbreaking works, including digital immunity, negative authentication, cloud insurance model, and auth-spectrum, have earned recognition in Computer World Magazine and other media outlets.  He received research funding from different federal agencies including NSF, DARPA, IARPA, NSA, NAVY, ONR, DoD and DHS/FEMA. At the National Cyber Leap Year Summit in 2009, Dr. Dasgupta served as a Co-Chair for the Health-Inspired Network Defense working group (see the report, section 6, starting page 46), the results of which have led to a new research program within the Department of Homeland Security’s Science and Technology. With over 300 publications (including 4 patents), 22000+ citations, and an h-index of 68, Dr. Dasgupta’s multidisciplinary research is highly acclaimed. He has received numerous awards, including the 2012 Willard R. Sparks Eminent Faculty Award and the 2014 ACM SIGEVO Impact Award. He also received five best paper awards in different international conferences and has organized Symposia on Computational Intelligence in Cyber Security at IEEE SSCI during 2007-2023. Dr. Dasgupta is an IEEE Fellow, AIIA Fellow and NAI Fellow, an ACM Distinguished Speaker (2015-2020), an IEEE Distinguished Lecturer (2022-2024) and 2024 NSF-Fulbright Distinguished Scholar. He regularly serves as a panelist and keynote speaker and offers tutorials in leading computer science conferences and has given more than 350 invited talks in different universities and industries.

Host: Viktor Prasanna, prasanna@usc.edu

Published on April 28th, 2025Last updated on April 28th, 2025