Sudharshan Balaji

@bsudharshan2001

Ph.D. researcher at University of South Florida, working in the SPRAI Lab[1] with Dr. Ning Wang. I spend my days making AI systems less mysterious and more secure.

My work sits at the intersection of large language models, federated learning, and medical NLP. Currently obsessed with how LLMs behave (and misbehave) in security-critical contexts.

Previously finished my Master's here at USF[2] where I discovered the peculiar joy of debugging Flask apps at midnight. Outside of research, I watch football (the European kind), catch F1 races, and convince myself I'll finish my side projects someday.

Recent
Aug 2025 Started PhD continuing under Dr. Ning Wang
May 2025 Graduated with Master's in CS from USF
Apr 2025 Thesis on LLMs for Network Intrusion Detection published to ProQuest
Feb 2025 Defended thesis successfully
Sep 2024 Started TA'ing "Security & Privacy in ML"
Mar 2024 Joined SPRAI Lab with Dr. Ning Wang