Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Faranak Abri
Second Advisor
Fabio Di Troia
Third Advisor
Thomas Austin
Keywords
Large Language Models, Gen AI, voice cloning
Abstract
Large Language Models (LLMs) have quickly gone from simple rule-based systems to complex knowledge bases capable of tackling many different tasks across a variety of fields. What began as an exercise in human-computer interaction has become the basis for artificial intelligence in a variety of mediums. When attached to larger systems, LLMs become generative assistants that can perform highly on human proficiency assessments and other benchmark skill assessments. This increase in proficiency has led these systems to be deployed in fields such as cybersecurity, business, and programming to help improve productivity and efficiency. However, such a wide availability has allowed threat actors to abuse these systems to achieve many attacks. Defenses such as awareness, detection, and red teaming may not be able to keep up with the pace of these attacks. This paper shows our research on the current state of LLMs and their role in Gen AI. In addition, we present an experiment on how LLMs can be combined with voice cloning to create a platform for social engineering attacks.
Recommended Citation
Valdez, Hezekiah Paul D., "Exploring the Use and Misuse of Large Language Models (LLMs)" (2024). Master's Projects. 1440.
https://scholarworks.sjsu.edu/etd_projects/1440
