Secure autonomy
Protect the value of agent autonomy by giving it a trustworthy operating boundary.
ABOUT WHITZARD
Security infrastructure for the agentic AI era
Whitzard develops security infrastructure for AI agents. AgentGuard, Model Services, NUWA research, and the open ecosystem connect evaluation, runtime protection, and audit.
OUR WORK
Products, research, and open technology
AgentGuard
Core enterprise productA unified security control layer across the full agent runtime.
→NUWA
Frontier AI safety researchResearch that defines risk, builds evaluation evidence, and advances safety models.
→Whitzard Open Ecosystem
Open ecosystemPublic models, tools, data, and evaluation infrastructure.
→Team vision
Evidence before claims
Ground every claim in public sources, evaluations, and deployment evidence.
Research into control
Translate risk understanding into precise interventions in real systems.
Public safety goods
Build verifiable, reusable models, tools, data, and evaluation infrastructure.
Founders
Founded by Jiarun Dai and Xudong Pan, with expertise in systems security and AI safety.
Dr. Jiarun Dai
CEOCEO of Whitzard and Associate Research Professor at Fudan University. His research focuses on binary analysis, vulnerability discovery, and exploitation. He holds a PhD from Fudan University and previously captained the Fudan Baize CTF team.
Dr. Xudong Pan
CTOCTO of Whitzard, Associate Research Professor at Fudan University, and PhD advisor at the Shanghai Innovation Institute. His research covers AI safety, model safety, systems security, and frontier-risk evaluation. He holds a PhD from Fudan University.