About
I am a 4th year Ph.D. candidate in Computer Science at the University of Southern California (USC), advised by Dr. Chao Wang.
My research lies at the intersection of Software Engineering (SE) and Artificial Intelligence (AI). My work spans both SE for AI – evaluating and verifying AI systems for reliability and fairness – and AI for SE – leveraging AI and LLMs to improve program analysis and verification. Please refer to my CV for more information.
Prior to joining USC, I graduated cum laude with a B.S. in Computer Science from New York University Abu Dhabi (NYUAD), where I worked on browser security under Dr. Christina Pöpper. Outside of work, I enjoy reading, clarinet, and tennis!
Recent News
02/2026: Serving as Publicity Chair for HARMONY 2026 — I am serving as Publicity Chair for HARMONY 2026, an IEEE/ACM CHASE 2026 workshop around AI and mental health. Our CFP is open, so we welcome all submissions, from both computing and non-computing experts!
02/2026: Selected to Give Talk at SoCalPLS 2026 — I have been selected to give a talk about my work on LLMs for mental health diagnosis at SoCalPLS 2026, hosted right here at USC in Los Angeles, CA! An important topic to me, which I’m excited to share with the PL community!
12/2025: Guest Lecture at CSU Long Beach — I had the pleasure of giving my first guest lecture at CSU Long Beach for Dr. Xin Qin’s course! I talked about the field of machine learning verification and presented my work on fairness verification. I hope the students found it interesting :)
11/2025: Paper Accepted to NLDL 2026 — Our work on counterfactual dataset generation to falsify individual fairness on neural networks has been accepted to NLDL 2026. See you in Tromsø, Norway!
10/2025: Invited to the 1st Meta PhD Forum — I was invited to join other PhD students and present my research at Meta’s Menlo Park HQ for the inaugural Meta PhD Forum!
Publications
Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation. Brian Hyeongseok Kim, Jacqueline L. Mitchell, and Chao Wang. NLDL 2026, Tromsø, Norway.
FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks. Brian Hyeongseok Kim, Jingbo Wang, and Chao Wang. ICSE 2025, Ottawa, Canada.
Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters. Jacqueline L. Mitchell, Brian Hyeongseok Kim, Chenyu Zhou, and Chao Wang. LMPL workshop @ SPLASH 2025, Singapore.
Large Language Models for Interpretable Mental Health Diagnosis. Brian Hyeongseok Kim and Chao Wang. GenAI4Health workshop @ AAAI 2025, Philadelphia, USA.
Extending Browser Extension Fingerprinting to Mobile Devices. Brian Hyeongseok Kim, Shujaat Mirza, and Christina Pöpper. WPES workshop @ CCS 2025, Copenhagen, Denmark.
Personal
- I am actively running a book review / reflection blog. Let me know if you have any book recommendations.
- I am a member of the Heart of Los Angeles Eisner Intergenerational Orchestra, where I play the clarinet. Please join us if you are a music enthusiast based in LA!
- I have lived in 6 different countries and have documented my past experiences here and there.
- I am learning Spanish and Tagalog. Help me practice, por favor / pakiusap!