About

I am a 4th year Ph.D. candidate in Computer Science at the University of Southern California (USC), where I am advised by Prof. Chao Wang. My interests lie at the intersection of artificial intelligence (AI) and software engineering (SE). Specifically, my research spans both SE for AI – evaluating and verifying AI systems for reliability and fairness – and AI for SE – leveraging AI and large language models (LLMs) to improve program analysis and verification. I integrate advanced AI techniques with classic SE methods such as SMT solving, symbolic execution, abstract interpretation, and logic programming.

Prior to joining USC, I received my B.S. in Computer Science from New York University Abu Dhabi (NYUAD), where I worked on browser security under Prof. Christina Pöpper.

For more information, please refer to my CV.

Recent News

  • 10/2025: My projects during my internship at AWS have been honored with:
    • Code Analysis for AI Agent Tools has been accepted to the Trustworthy Agentic AI Workshop, part of AMLC 2025 (Amazon Machine Learning Conference)!
    • Automated AI Guardrail Creation and Correction has been published as part of the AWS Samples GitHub repository!
  • 08/2025: Our work on analyzing LLM failures in abstract interpretation reasoning has been accepted to LMPL, a SPLASH 2025 workshop!
  • 05/2025: I am working as an Applied Scientist Intern with the AWS Provable Security & Automation team for the summer in New York City, USA!
  • 04/2025: I was awarded a Best Reviewer Award for AISTATS 2025!
  • 01/2025: Our work on LLMs for mental health diagnosis has been accepted to GenAI4Health, a AAAI 2025 workshop. See you in Philadelphia, USA!
  • 12/2024: I have passed my qualifying exam!
  • 07/2024: Our work on neural network verification of individual fairness has been accepted to ICSE 2025. See you in Ottawa, Canada!
  • 05/2024: I will be attending the Verification Mentoring Workshop (VMW) at CAV 2024 in July. See you in Montreal, Canada!
  • 04/2024: I will be attending the Programming Languages Mentoring Workshop (PLMW) at PLDI 2024 in June. See you (back) in Copenhagen, Denmark!
  • 04/2024: I will be attending the 13th Summer School on Formal Techniques (SSFT) in May. See you in San Francisco, California!
  • 09/2023: Our work on mobile browser extension fingerprinting has been accepted to WPES, a CCS 2023 workshop. See you in Copenhagen, Denmark!

Publications

  • FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks [paper] [proceedings] [arXiv] [code] [slides]
    Brian Hyeongseok Kim, Jingbo Wang, and Chao Wang. The IEEE/ACM International Conference on Software Engineering (ICSE), Ottawa, Canada, 2025.
  • Large Language Models for Interpretable Mental Health Diagnosis [OpenReview] [arXiv] [poster]
    Brian Hyeongseok Kim and Chao Wang. Workshop on Large Language Models and Generative AI for Health at the AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, USA, 2025.
  • Extending Browser Extension Fingerprinting to Mobile Devices [proceedings] [code] [slides]
    Brian Hyeongseok Kim, Shujaat Mirza, and Christina Pöpper. Workshop on Privacy in the Electronic Society at the ACM Conference on Computer and Communications Security (CCS), Copenhagen, Denmark, 2023.

Personal

  1. I am actively running a book review / reflection blog. Let me know if you have any book recommendations.
  2. 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!
  3. I have lived in 6 different countries and have documented my past experiences here and there.
  4. I am learning Spanish and Tagalog. Help me practice, por favor / pakiusap!