Guanqun Yang 杨冠群
 |
Ph.D. Candidate in Computer Science Email: gyang16@stevens.edu or guanqun.yang@outlook.com Office: Room 433, Gateway South Hall (Google Map) LinkedIn | GitHub | Google Scholar | Semantic Scholar | ORCID |
About Me
I specialize in developing applications that leverage Large Language Models (LLMs) for security and software engineering. My projects reflect a commitment to enhancing security protocols and automating complex processes. Here are a few highlights:
LLM-based Verification of Security Vulnerability Reports: Automating the evidence collection for proposed security vulnerability with LLM agents.
Continuous Automated Red Teaming of LLMs: Identifying weaknesses in hate speech defense by generating targeted test samples.
LLM-based Test Case Generator for SLMs: Developing efficient test cases for managing NLP models on HuggingFace Hub.
Automated Management of Security Vulnerability Reports using NER: Streamlining the handling of software names and versions in vulnerability reports using named entity recognition (NER).
I am fortunate to be advised by Prof. Xueqing (Susan) Liu. Before coming to Stevens, I received my master's degree in Electrical and Computer Engineering from UCLA in 2019. I was working with Prof. Quanquan Gu and Prof. Vwani P. Roychowdhury on the theoretical and application aspect of algorithmic fairness in machine learning systems (my master thesis). I received my Bachelor's degree in Electrical Engineering from Northeastern University, China in 2017.
Education
Recent Activities
[2024-06-03] Started interning at Capital One as a data scientist working on LLM-based chatbots.
[2023-07-11] Gave a tutorial on AI and ChatGPT to underrepresented high school students. You can find full details in my post on LinkedIn. The slide and notebook is available on GitHub.
Miscellaneous
Besides NLP research, I love opera, live music (classical and not-so classical alike), and hiking. See my reviews of the performances and trail routes here.
I am also on Twitter, click the icon to follow.