OpenAI said on 23 October that it and Poland’s NASK National Research Institute had signed an agreement to explore joint work on AI safety, security and technical research. The agreement brings NASK’s AI Safety Research Center, which serves as Poland’s Artificial Intelligence Safety Institute, into planned research with OpenAI on evaluating AI systems, finding potential vulnerabilities and strengthening safeguards.
Radosław Nielek, NASK’s director, said the centre’s work includes detecting synthetic AI-generated content and studying malicious uses of AI. OpenAI also cited its existing work with the US Center for Advancing Standards and Innovation for Super Intelligence and the UK AI Security Institute.
The agreement follows a July collaboration with CERT Polska, a computer emergency response team within NASK. OpenAI said the team gained access to its cyber-capable models through Daybreak and used them to help find six vulnerabilities in MikroTik RouterOS. Some of the flaws could be combined to take control of affected devices without authentication. MikroTik released fixes, which OpenAI said CERT Polska confirmed prevented the attacks it had observed.
