NEWSROOM
News
Research updates, company news, and open-source releases from Whitzard and NUWA.
Featured
Highlighted updates from Whitzard and NUWA.
AgentCyberRange: Evaluating autonomous cyber capabilities over long-horizon tasks
Starting with limited target information, AgentCyberRange evaluates how agents discover attack surfaces, exploit vulnerabilities, and carry access, credentials, and network reachability through a multistage attack. Access requests from 100+ research institutions worldwide.
Source: NUWA Frontier AI Safety LabThe Science of Frontier AI Risk Evaluation
NUWA's first public research essay on making frontier AI risk evaluation more scientific, evidence-based, and operational.
Source: NUWA SubstackNUWA Launch
NUWA Frontier AI Safety Lab launches with support from Whitzard.
Source: WhitzardLatest
Recent updates and announcements.
Fudan Baize CyberGym evaluation results
A Chinese report notes that Fudan Baize's Whitzard agent reached a 91.2% success rate on CyberGym, ranking second globally and first among universities.
Source: Fudan Baize WeChat official account · Chinese sourceWhitzardAgent Open Ecosystem
WhitzardAgent hosts open-source tools and datasets for AI safety evaluation, agent safety, and runtime protection.
Source: GitHub