Short bio: I am an assistant professor and Zhu Chair at UCSB CS. I completed my Postdoc at UC Berkeley as part of the RDI center and BAIR Lab, under the mentorship of Prof. Dawn Song. I received my Ph.D. from Penn State with Prof. Xinyu Xing and my master's degree from Shanghai Jiao Tong University. Outside of research, I am the Head of Agent Security at Virtue AI, a startup focusing on frontier AI security.
My research interests center around the intersection of machine learning and security. My current research focus on LLM code reasoning and agentic models, AI agents for security and SE, and agent security and safety. My previous works studied the trustworthiness of DRLs, DNNs and designing DNNs for security applications (noisy learning, OODs).
- Academic Senate Faculty Research Award, UCSB, 2025
- Google ML and Systems Junior Faculty Award, Google, 2025
- Berkeley RDI AI & Decentralization Innovation Award, UC Berkeley, 2025
- Amazon Research Award (with Christopher Kruegel), Amazon, 2024
- FAR AI Research Award, FAR AI, 2024
- DARPA AIxCC Finalist (Top 7), DARPA, 2024
- Google SBFT Fuzzing Tool Competition Award (Top 1), ACM, 2024
- IBM Fellowship Award, IBM, 2020
- Facebook Fellowship Finalist, Facebook, 2020
- Baidu AI Fellowship Finalist, Baidu, 2020
- CCS Outstanding Paper Award, ACM, 2018
- Black Hat Student Scholarship, Black Hat, 2018-2020
- Multiple Conference Travel Grants (e.g., USENIX Security, CCS, NeurIPS, ICML), 2018-2021
-
DARPA AIxCC
Top 7, August, 2024 (Press release: Washington post)
-
SWE-bench-Verfied: PatchPilot ranked in the top five open source tools; PatchPilot+co-PatcheR ranked second in the open weighted model
-
I play CTFs with Shellphish
-
Geekpwn Competition on Data Tracing CTF
Top 10, August, 2018
-
Geekpwn Competition on Advesarial Attacks and Defenses CTF
Finalist (Top 6 worldwide), August, 2018 (Press release: CCTV, CSDN, TOM)
-
Kanxue AI CTF
Competition Question Maker, June, 2018 (Press release: China Daily, kknews)
I am actively recruiting Ph.D. students. If you have a solid background in LLMs, DRL, or software security skills (static analysis, fuzzing, symbolic execution) and are interested in working with me, please do not hesitate to contact me through email.
Copyright © Wenbo Guo
