ResearchOpenAI

OpenAI and Poland's NASK partner on AI safety

Original title: OpenAI and Poland’s NASK partner to advance AI safety and security

Plain language

What it is: OpenAI and Poland's NASK National Research Institute have signed an agreement to partner on AI safety, security, and technical research. The partnership aims to better understand risks and strengthen safeguards for AI systems.
How it works: The organizations will combine their research expertise and technical capabilities. They will work together to evaluate AI systems, identify potential vulnerabilities, and study synthetic AI-generated content.
Where it is available: This partnership applies to OpenAI and NASK's AI Safety Research Center, which serves as the Polish Artificial Intelligence Safety Institute.
Example: A team within NASK used OpenAI models to find six security vulnerabilities in MikroTik RouterOS, which allowed the vendor to release fixes.

What it is: OpenAI and Poland's NASK have partnered to collaborate on technical research, AI safety, and security. The agreement focuses on evaluating capable AI systems and identifying vulnerabilities.
How it works: The collaboration involves sharing expertise to develop safeguards against emerging risks, detect synthetic content, and analyze multilingual challenges. It also builds on previous work where cyber defenders used OpenAI's cyber capable models.
Where it is available: The collaboration is established between OpenAI and NASK's AI Safety Research Center in Poland.
Example: CERT Polska used OpenAI's cyber capable models through Daybreak to discover six vulnerabilities in MikroTik RouterOS, including flaws that could allow unauthorized device control.

The headline and explanation on this page are based on OpenAI's post. The full details are in the original.

OpenAI and Poland’s NASK partner to advance AI safety and security