New research at the Blavatnik School of Government on how to protect advanced AI systems from malicious attacks has been supported by a grant from Open Philanthropy.
As advanced AI systems become more capable, there is an increased risk that these systems will be subject to theft, manipulation, and abuse from malicious actors. The project team will explore how governments and frontier AI organisations can collaborate to implement standards for protecting these systems.
The project will be co-led by Ciaran Martin, Professor of Practice and founding Chief Executive of the National Cyber Security Centre, Dr Brianna Rosen, Senior Research Associate at the Blavatnik School, and Dr Robert Trager, Senior Research Fellow at the School and Co-Director of the Oxford Martin AI Governance Initiative.
The project aims to develop a set of actionable recommendations for how key stakeholders can work together to improve AI security. More details about the research can be found on the project's webpage.
Recent news
MPP and MSc alumnus Carlos Santiago Guzmán wins the inaugural Michael Cichon Graduate Award
Carlos Santiago Guzmán Gutiérrez, an alumnus of the Master of Public Policy and the MSc in Public Policy Research, has received the inaugural Michael Cichon Graduate Award for outstanding master’s thesis in Social Protection. The award recognises his MSc thesis, “Universal Social Protection Schemes in Forced Displacement Settings: Evidence from Colombia.”
