Sakana AI Blog· Sakana AI·· 21 hr agoAI score38
Introducing Sakana AI’s Security Research Group
Introducing Sakana AI’s Security Research Group
AI summary
Sakana AI announced a Security Research Group, an independent R&D team separate from its commercial business, focused on collective AI-driven cyber defense and on the security and safety of AI itself. The group plans to publish research, reproducible benchmarks and practical guidelines, and to work with government, industry and academia, with long-term emphasis on upstream, secure-by-design prevention rather than post-release patching. It is led by Akihiro Umegai and David Ha, and cites prior work including Digital Red Queen, ShinkaEvolve and Fugu-Cyber, which Sakana AI reports reached 86.9% on CyberGym and 72.1% on CTI-REALM.
Source: Sakana AI Blog · sakana.ai