NUWA FRONTIER AI SAFETY LAB
NUWA Frontier AI Safety Lab advances frontier AI risk research and governance through reproducible evidence, evaluation methods, and public goods.
Research scope
Frontier AI risk research and governance
NUWA · RESEARCH HIGHLIGHT
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
Selected institutions requesting access
RESEARCH & MEDIA COVERAGE
Controlled experiments examining agents' capacity for self-replication, their behavior, and the limits of human control.
GLOBAL AI SAFETY GOVERNANCE
NUWA Lab is deeply involved in international AI safety consensus, research priorities, and generative AI safety standards.
CONSENSUS & RESEARCH PRIORITIES
Alignment · Human control · Verifiable red lines
Deep involvement from NUWA Lab
An international scientific consensus on alignment, human control, safety assurance, and verifiable behavioural red lines for advanced AI.
CONSENSUS & RESEARCH PRIORITIES
Risk assessment · Safe development · Control · Societal resilience
Deep involvement from NUWA Lab
A global agenda for urgent AI safety research shaped by contributors from frontier developers, government safety institutes, academia, and civil society.
NATIONAL STANDARD
Cybersecurity technology—Basic security requirements for generative artificial intelligence service
Deep involvement from NUWA Lab
A national baseline for training-data security, model security, service safeguards, and security assessment of generative AI services.
Research focus
We study risks arising from autonomous AI systems and develop evidence-based methods for evaluation, governance, and control.
Study autonomy, deception, scheming, loss of control, and emerging agent behavior that becomes possible as capabilities grow.
Develop executable environments, benchmarks, methodologies, and public research records that make frontier risk observable and comparable.
Turn risk understanding into lightweight models for reasoning, intent, trust, and runtime defense.
Use research evidence to inform AgentGuard policies and operational feedback to refine evaluations.
RESEARCH PROGRAMS
Study risks from increasingly capable and autonomous AI systems and develop verifiable approaches to control.
Autonomy · Deception · Scheming · Loss of control02Study systemic safety questions in reasoning, action, tool use, model behavior, and human–AI trust.
Agent behavior · Model safety · Tool use · Trustworthy interaction03Build executable, reproducible evaluations and study how evidence should inform risk assessment and governance decisions.
Capability evaluation · Risk assessment · Evaluation environments · Governance methodsResearch infrastructure
Public evaluation environments and benchmarks that make agent cybersecurity capability observable.
Evaluates frontier AI systems' autonomous cyber-attack capabilities in complex enterprise environments.
Official site ↗Synthesizes executable test environments that combine deterministic code state with narrative dynamics for frontier AI risk evaluation.
Official site ↗COLLABORATION
Connect with us on frontier-risk evaluation, agent safety, AI control, and open technical evidence.
