Updating the Frontier Safety Framework
… Given the stakes involved as we look ahead to increasingly powerful AI, getting this wrong could have serious implications for safety and security. …
Search
Google DeepMind and partners announce multi-agent safety research funding call.
June 11, 2026 Responsibility & Safety Investing in multi-agent AI safety research Google DeepMind, Schmidt Sciences, the Cooperative AI Foundation, ARIA and Google.org For the past decade, we’ve focused on making individual AI models more capable, helpful and safe. …
Taking a responsible path to AGI
… This includes sophisticated security mechanisms which could prevent malicious actors from obtaining raw access to model weights that allow them to bypass our safety guardrails; mitigations that limit the potential for misuse when the model is deployed; and threat modelling research that helps ident… …
Introducing CodeMender: an AI agent for code security
October 6, 2025 Responsibility & Safety Introducing CodeMender: an AI agent for code security Raluca Ada Popa and Four Flynn Today, we’re sharing early results from our research on CodeMender, a new AI-powered agent that improves code security automatically. …
Securing internal systems against increasingly capable and imperfectly aligned AI
… Understanding these nuances is critical for refining our safety and security protocols. Defending the agent ecosystem is a shared responsibility The AI Control Roadmap is one vital element of our multilayered approach to agent security. …
Introducing the Frontier Safety Framework
… Risk domains and mitigation levels Our initial set of Critical Capability Levels is based on investigation of four domains: autonomy, biosecurity, cybersecurity, and machine learning research and development R&D . …
Google DeepMind and Korea Partner to Accelerate Scientific Discovery
… Finally, following our Frontier AI Safety Commitments made at the AI Seoul Summit, we will collaborate with the Korean AI Safety Institute AISI on research and best practices. …
Looking ahead to the AI Seoul Summit
… This progress on AI capabilities promises to improve many people’s lives, but also raises novel questions that need to be tackled collaboratively in a number of key safety domains. Google DeepMind is working to identify and address these challenges through pioneering safety research. …
Building secure AGI: Evaluating emerging cyber security capabilities of advanced AI
April 2, 2025 Responsibility & Safety Evaluating potential cybersecurity threats of advanced AI Four Flynn, Mikel Rodriguez and Raluca Ada Popa But to harness such benefits, we must also understand and mitigate the risks of increasingly advanced AI being misused to enable or enhance cyberattacks. …
Google DeepMind and Isomorphic Labs approach to bioresilience
… We are committed to working openly and collaboratively — with biosecurity labs, governments and the broader scientific community — to ensure AI is developed and deployed responsibly to help protect against one of society’s greatest risks. …