Publication

Publication

Conference Papers

  • Alessio Bucaioni, Martin Weyssow, Junda He, Yunbo Lyu, David Lo. "Artificial Intelligence for Software Architecture: Literature Review and the Road Ahead" FSE 2025 - 2030 Software Engineering Workshop. (11 pages)
  • Alessio Bucaioni, Martin Weyssow, Junda He, Yunbo Lyu, David Lo. "A Functional Software Reference Architecture for LLM-Integrated Systems" 2025 IEEE 22nd International Conference on Software Architecture (ICSA). (5 pages, New and Emerging Ideas Track.)
  • Yunbo Lyu, Thanh Le-Cong, Hong Jin Kang, Ratnadira Widyasari, Zhipeng Zhao, Xuan-Bach D. Le, Ming Li, David Lo. "CHRONOS: Time-Aware Zero-Shot Identification of Libraries from Vulnerability Reports" 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE). (12 pages, Technical Track.)

Journal Article

  • Yunbo Lyu, Hong Jin Kang, Ratnadira Widyasari, Julia Lawall, David Lo. "Evaluating SZZ Implementations: An Empirical Study on the Linux Kernel" IEEE Transactions on Software Engineering, FSE 2025 Journal-First

Preprints

  • Yunbo Lyu, Zhou Yang, Yuqing Niu, Jing Jiang, David Lo. "Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?"
  • Zhou Yang, Zhensu Sun, Yunbo Lyu, Terry Zhuo Yue, Premkumar Devanbu, David Lo. Robustness, security, privacy, explainability, efficiency, and usability of large language models for code.
  • Hong Jin Kang, Yunbo Lyu, Pattarakrit Rattanukul, Stefanus Agus Haryono, Truong Giang Nguyen, Chaiyong Ragkhitwetsagul, Corina Pasareanu, David Lo. "Active Learning-based Input Selection for Fuzzing Deep Learning Libraries" (This work found vulnerabilities leading to the assignment of 23 CVEs)
  • Chengran Yang, Jiakun Liu, Bowen Xu, Christoph Treude, Yunbo Lyu, Junda He, Ming Li, David Lo. "APIDocBooster: An Extract-Then-Abstract Framework Leveraging Large Language Models for Augmenting API Documentation"
  • Xin Zhou, Martin Weyssow, Ratnadira Widyasari, Ting Zhang, Junda He, Yunbo Lyu, Jianming Chang, Beiqi Zhang, Dan Huang, David Lo. "LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks." (Under review at TOSEM.)