FHI is pleased to announce the publication of a report involving several of our researchers, entitled “The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation.”
This report was written by researchers at the Future of Humanity Institute, the Center for the Study of Existential Risk, OpenAI, the Electronic Frontier Foundation, the Center for a New American Security, and 9 other institutions, drawing on expertise from a wide range of areas, including AI, cybersecurity, and public policy.
This report distils findings from a workshop held last year as well as additional research done by the authors. It explores possible risks to security posed by malicious applications of AI in the digital, physical, and political domains, and lays out a research agenda for further work in addressing such risks.
Lead author and FHI Research Fellow Miles Brundage writes: “We’re very excited to finally get this work out to a wider audience. The malicious use of AI poses complex challenges and tradeoffs, and making progress on it will require drawing on the expertise of far more people than could fit into a two-day workshop. We look forward to hearing different stakeholders’ reactions to the report and continuing to move this discussion forward.”
The text of the report can be found at www.maliciousaireport.com.