HK
Hong Jin Kang
cs.SEcs.CRcs.AIcs.LGcs.CLcs.FLcs.HCcs.PFcs.PL
On Valency
published · living versionsW_9zv6edxy·v1 · currentpublished
Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance
with Xi Zheng, Ivan Ruchkin, Tevfik Bultan, Vijay Ganesh +9
1 version
W_hwsxy87x·v1published
Preprints & journals
40 papers in the corpus · 2016–2026PoCEvolve: Generating Proof-of-Concept Exploits from Security Patches with Vulnerability-Aware Prompt Evolution2607.22076v1 · Duc Manh Tran, Ratnadira Widyasari, Ivana Clairine Irsan et al.2026 · 0 citationsarXiv
An Empirical Comparison of General Context-Free Parsers2606.08465v1 · Huan Vo, Danushka Liyanage, Hong Jin Kang et al.2026 · 0 citationsarXiv
TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEs2604.17860v3 · Ting Zhang, Yikun Li, Chengran Yang et al.2026 · 0 citationsarXiv
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits2604.02665v1 · Yunbo Lyu, Jieke Shi, Hong Jin Kang et al.2026 · 0 citationsarXiv
Revisiting Vulnerability Patch Identification on Data in the Wild2603.17266v1 · Ivana Clairine Irsan, Ratnadira Widyasari, Ting Zhang et al.2026 · 0 citationsarXiv
TensorCommitments: A Lightweight Verifiable Inference for Large Language Models2602.12630v3 · Oguzhan Baser, Elahe Sadeghi, Eric Wang et al.2026 · 0 citationsarXiv
SWIRL: Interactive Sensemaking of Tool-Generated Warnings through Customized Summaries2508.07169v2 · Burak Yetistiren, Hong Jin Kang, Miryung Kim2025 · 0 citationsarXiv
WhyFlow: Interrogative Debugger for Sensemaking Taint Analysis2508.07198v3 · Burak Yetistiren, Hong Jin Kang, Miryung Kim2025 · 0 citationsarXiv
Back to the Basics: Rethinking Issue-Commit Linking with LLM-Assisted Retrieval2507.09199v3 · Huihui Huang, Ratnadira Widyasari, Ting Zhang et al.2025 · 0 citationsarXiv
Mapping NVD Records to Their Vulnerability-fixing Commits: How Hard is It?2506.09702v2 · Huu Hung Nguyen, Ting Zhang, Duc Manh Tran et al.2025 · 0 citationsarXiv
Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents2505.10961v2 · Ratnadira Widyasari, Martin Weyssow, Ivana Clairine Irsan et al.2025 · 3 citationsarXiv
Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning2503.14838v1 · Chengran Yang, Zhensu Sun, Hong Jin Kang et al.2025 · 0 citationsarXiv
Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection2503.01449v1 · Ting Zhang, Chengran Yang, Yindu Su et al.2025 · 0 citationsarXiv
Towards Reliable LLM-Driven Fuzz Testing: Vision and Road Ahead2503.00795v1 · Yiran Cheng, Hong Jin Kang, Lwin Khin Shar et al.2025 · 0 citationsarXiv
Grey-Box Fuzzing in Constrained Ultra-Large Systems: Lessons for SE Community2501.10269v3 · Jiazhao Yu, Yanlun Tu, Zhanlei Zhang et al.2025 · 1 citationarXiv
ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models2412.17264v1 · Chengran Yang, Hong Jin Kang, Jieke Shi et al.2024 · 0 citationsarXiv
CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics2411.17274v7 · Yikun Li, Ting Zhang, Ratnadira Widyasari et al.2024 · 5 citationsarXiv
JavaVFC: Java Vulnerability Fixing Commits from Open-source Software2409.05576v1 · Tan Bui, Yan Naing Tun, Yiran Cheng et al.2024 · 0 citationsarXiv
Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking2404.18881v1 · Hong Jin Kang, Fabrice Harel-Canada, Muhammad Ali Gulzar et al.2024 · 8 citationsarXiv
Fuzzing MLIR Compilers with Custom Mutation Synthesis2404.16947v2 · Ben Limpanukorn, Jiyuan Wang, Hong Jin Kang et al.2024 · 5 citationsarXiv
BugsInPy: A Database of Existing Bugs in Python Programs to Enable Controlled Testing and Debugging Studies2401.15481v1 · Ratnadira Widyasari, Sheng Qin Sim, Camellia Lok et al.2024 · 150 citationsProceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (2020) 1556-1560
Greening Large Language Models of Code2309.04076v3 · Jieke Shi, Zhou Yang, Hong Jin Kang et al.2023 · 35 citationsarXiv
Evaluating SZZ Implementations: An Empirical Study on the Linux Kernel2308.05060v2 · Yunbo Lyu, Hong Jin Kang, Ratnadira Widyasari et al.2023 · 11 citationsarXiv
Multi-Granularity Detector for Vulnerability Fixes2305.13884v1 · Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang et al.2023 · 28 citationsIEEE Transactions on Software Engineering, 2023
CHRONOS: Time-Aware Zero-Shot Identification of Libraries from Vulnerability Reports2301.03944v4 · Yunbo Lyu, Thanh Le-Cong, Hong Jin Kang et al.2023 · 25 citationsarXiv
Stealthy Backdoor Attack for Code Models2301.02496v2 · Zhou Yang, Bowen Xu, Jie M. Zhang et al.2023 · 77 citationsarXiv
SkipFuzz: Active Learning-based Input Selection for Fuzzing Deep Learning Libraries2212.04038v1 · Hong Jin Kang, Pattarakrit Rattanukul, Stefanus Agus Haryono et al.2022 · 7 citationsarXiv
AutoPruner: Transformer-Based Call Graph Pruning2209.03230v1 · Thanh Le-Cong, Hong Jin Kang, Truong Giang Nguyen et al.2022 · 21 citationsarXiv
VulCurator: A Vulnerability-Fixing Commit Detector2209.03260v1 · Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang et al.2022 · 38 citationsarXiv
Compressing Pre-trained Models of Code into 3 MB2208.07120v2 · Jieke Shi, Zhou Yang, Bowen Xu et al.2022 · 47 citationsarXiv
How to Find Actionable Static Analysis Warnings: A Case Study with FindBugs2205.10504v2 · Rahul Yedida, Hong Jin Kang, Huy Tu et al.2022 · 19 citationsarXiv
Active Learning of Discriminative Subgraph Patterns for API Misuse Detection2204.09945v1 · Hong Jin Kang, David Lo2022 · 26 citationsarXiv
Detecting False Alarms from Automatic Static Analysis Tools: How Far are We?2202.05982v1 · Hong Jin Kang, Khai Loong Aw, David Lo2022 · 51 citationsarXiv
Adversarial Specification Mining2103.15350v1 · Hong Jin Kang, David Lo2021 · 12 citationsACM Transactions on Software Engineering and Methodology (TOSEM) 30.2 (2021): 1-40
BiasFinder: Metamorphic Test Generation to Uncover Bias for Sentiment Analysis Systems2102.01859v2 · Muhammad Hilmi Asyrofi, Zhou Yang, Imam Nur Bani Yusuf et al.2021 · 67 citationsarXiv
AndroEvolve: Automated Update for Android Deprecated-API Usages2012.07259v2 · Stefanus Agus Haryono, Ferdian Thung, David Lo et al.2020 · 18 citationsarXiv
AndroEvolve: Automated Android API Update with Data Flow Analysis and Variable Denormalization2011.05020v1 · Stefanus A. Haryono, Ferdian Thung, David Lo et al.2020 · 24 citationsarXiv
Automatic Android Deprecated-API Usage Update by Learning from Single Updated Example2005.13220v1 · Stefanus Agus Haryono, Ferdian Thung, Hong Jin Kang et al.2020 · 38 citationsarXiv
CC2Vec: Distributed Representations of Code Changes2003.05620v1 · Thong Hoang, Hong Jin Kang, Julia Lawall et al.2020 · 175 citationsarXiv
A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation1611.02956v3 · Hong Jin Kang, Tao Chen, Muthu Kumar Chandrasekaran et al.2016 · 4 citationsProceedings of the 3rd Workshop on Natural Language Processing Techniques for Educational Applications, pages 30 to 39, Osaka, Japan, December 12 2016
Career total: 59 works. 40 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.