Posts by Collection

portfolio

Portfolio item number 1

Short description of portfolio item number 1

Portfolio item number 2

Short description of portfolio item number 2

publications

Extending Browser Extension Fingerprinting to Mobile Devices

Published in Workshop on Privacy in the Electronic Society at CCS (WPES), 2023

We apply browser extension fingerprinting techniques to mobile devices and show how the actual extension-modified data can be used by attackers.

Recommended citation: Kim, B. H., Mirza, S., & Pöpper, C. (2023, November). Extending Browser Extension Fingerprinting to Mobile Devices. In Proceedings of the 22nd Workshop on Privacy in the Electronic Society (pp. 141-146). https://dl.acm.org/doi/abs/10.1145/3603216.3624955

Large Language Models for Interpretable Mental Health Diagnosis

Published in Workshop on Large Language Models and Generative AI for Health at AAAI (GenAI4Health), 2025

We propose a clinical decision-making support tool that integrates LLMs and constraint logic programming for interpretable mental health diagnosis.

Recommended citation: Kim, B. H., & Wang, C. Large Language Models for Interpretable Mental Health Diagnosis. In Workshop on Large Language Models and Generative AI for Health at AAAI 2025. https://openreview.net/forum?id=L5iBC2En9N

FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks

Published in IEEE/ACM International Conference on Software Engineering (ICSE), 2025

We introduce a way to formally certify and quantify individual fairness of deep neural networks using symbolic abstract interpretation.

Recommended citation: Kim, B. H., Wang, J., & Wang, C. (2025, April). FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks. In Proceedings of the IEEE/ACM 47th International Conference on Software Engineering (pp. 527-539). https://doi.ieeecomputersociety.org/10.1109/ICSE55347.2025.00016

Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters

Published in Workshop on Language Models and Programming Languages at SPLASH (LMPL), 2025

We investigate LLMs’ capabilities to formally reason as abstract interpreters and analyze thematic patterns in their reasoning failures.

Recommended citation: Mitchell, J., Kim, B. H., Zhou, C., & Wang, C. (2025, October). Understanding Formal Reasoning Failures in LLMs as Abstract Interpreters. In Proceedings of the 1st ACM SIGPLAN International Workshop on Language Models and Programming Languages (pp. 71-83). https://dl.acm.org/doi/10.1145/3759425.3763389

Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation

Published in Northern Lights Deep Learning Conference (NLDL), 2026

We introduce counterfactual datasets as a novel framework for analyzing fairness in neural networks by examining how small changes in training labels influence predictions.

Recommended citation: Kim, B. H., Mitchell, J., & Wang, C. (2026, January). Analyzing Fairness of Neural Network Prediction via Counterfactual Dataset Generation. In Northern Lights Deep Learning Conference (pp. 247-262). PMLR. https://proceedings.mlr.press/v307/kim26a.html

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015