Iām a Ph.D. student at UCSB SecLab, advised by Prof. Giovanni Vigna and Prof. Christopher Kruegel.
My research focuses on building trustworthy software systems in the age of AI. I pursue this goal from two complementary directions: leveraging AI to discover software flaws and improve software quality, and understanding and improving the correctness and reliability of AI-generated software and agentic systems. My work spans LLM-assisted fuzzing, automated software testing, and the evaluation of AI agents in software engineering workflows.
I have discovered over 30 previously unknown bugs in widely used software, including Adobe Acrobat Reader, Foxit PDF Reader, PDF-XChange Editor, and Vim, and worked with developers to address them. I have also participated in CTF competitions as a member of Shellphish.
š„ News
- 2026.06: Ā šš One paper is accepted by CCS 2026!
- 2026.01: Ā šš One paper is accepted by ICLR 2026!
- 2022.12: Ā šš One paper is accepted by ICSE 2023!
š Educations
- 2024.09 - now, Ph.D. in Computer Science, UC Santa Barbara.
š Publications
From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers
Suyue Guo, Stijn Pletinckx, Tianle Yu, Yigitcan Kaya, Saad Ullah, Wenbo Guo, Christopher Kruegel, Giovanni Vigna
DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
Yuheng Tang, Kaijie Zhu, Bonan Ruan, Chuqi Zhang, Michael Yang, Hongwei Li, Suyue Guo, Tianneng Shi, Zekun Li, Christopher Kruegel, Giovanni Vigna, Dawn Song, William Yang Wang, Lun Wang, Yangruibo Ding, Zhenkai Liang, Wenbo Guo
Operand-Variation-Oriented Differential Analysis for Fuzzing Binding Calls in PDF Readers
Suyue Guo, Xinyu Wang, Wei You, Bin Liang, Wenchang Shi, Yiwei Zhang, Jianjun Huang, Jian Zhang
- Artifact Evaluated with Reusable and Available badges.
š Honors and Awards
- 2025 Distinguished Reviewer for ICSE 2026 Shadow PC.
- 2021 Defcon World Final 7th (with Nu1L Team).
- 2020.11 National Scholarship (the highest honor for Chinese undergraduates).
š Professional Service
- Program Committee Member: ICSE 2027
- Shadow Program Committee Member: ICSE 2026
- External Reviewer: IEEE S&P 2025, ISSRE 2024, RAID 2023
š ļø Software Flaw Disclosures
My work in automated software testing has led to the discovery and coordinated disclosure of 35 software flaws assigned CVE identifiers across Adobe Acrobat Reader, Foxit PDF Reader, PDF-XChange Editor, and Vim. These findings help vendors improve software quality and reliability.
Selected disclosures:
- Adobe Acrobat Reader: CVE-2025-43575, CVE-2022-34234
- Foxit PDF Reader: CVE-2025-55307, CVE-2023-27366
- PDF-XChange Editor: CVE-2025-6661