I am a postgraduate research associate at the Centre for the Study of Existential Risk, focusing on the role of technology (mainly digital technologies, including machine learning, and future technologies) in global catastrophic and existential risks. I am a co-lead author of The Malicious Use of AI: Forecasting, Prevention and Mitigation, a many-authored, cross-institution report exploring foreseeable security challenges from malicious applications of machine learning in the 5-10 year horizon. In my work, I use diverse tools in collaboration with others to explore future risk scenarios and propose prevention and mitigation strategies; these tools include expert workshops, agent-based models, and scenario role-plays. Those investigations help us understand where technology is and isn't trustworthy, where and how we should place (or refuse to place) our trust in it, and what steps we can take now to have more trustworthy technology in the future.
