Scholar
Chengquan Guo
Google Scholar ID: ubFLQuEAAAAJ
University of Chicago
Software Engineering
LLM
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
43
H-index
2
i10-index
1
Publications
3
Co-authors
6
list available
Contact
Email
chengquanguo@uchicago.edu
GitHub
Open ↗
Publications
5 items
VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
2025
Cited
0
BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
2025
Cited
0
RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
2025
Cited
0
PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset
2025
Cited
0
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
2025
Cited
0
Resume (English only)
Academic Achievements
- Published Papers:
- RedCode (NeurIPS, 2024)
- GUARDSET-X (NeurIPS, 2025)
- MMDT (ICLR 2025)
- RedCodeAgent (Submitted to ICLR 2026)
- BlueCodeAgent (Submitted to ICLR 2026)
- Honors & Awards:
- Outstanding Graduate (top 3%, 2025)
- National Scholarship (top 2%, 2024)
- Provincial Government Scholarship (top 3%, 2023)
- First-Class Scholarship in Zhejiang University (top 3%, 2023 & 2024)
- Tencent Scholarship (2023)
- Outstanding Student (2022, 2023, 2024)
Research Experience
- RedCode: Risky Code Execution and Generation Benchmark for Code Agents
- GUARDSET-X: Multi-Domain, Policy-Grounded, AI Security Guardrail Benchmark
- MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
- RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents
- BlueCodeAgent: A Blue Teaming Agent Enabled by Automated Red Teaming for CodeGen AI
Education
- Degree: PhD
- School: University of Chicago
- Advisor: Prof. Bo Li
- Time: Current
- Major: Not specified
Background
- Research Interests: Trustworthy AI and its applications in software engineering and security
- Professional Field: Secure Learning Lab
- Introduction: A first-year PhD student at the University of Chicago's Secure Learning Lab, under the guidance of Prof. Bo Li
Co-authors
6 total
Bo Li
University of Illinois at Urbana–Champaign
Zinan Lin
Microsoft Research (Redmond), Carnegie Mellon University
Dawn Song
Professor of Computer Science, UC Berkeley
Chulin Xie
Google DeepMind
Zhaorun Chen
Ph.D. Student, UChicago CS
Andy Zhou
Intology AI
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up