Dr George Chalhoub
Assistant Professor
London WC1E 6EA, UK
Cambridge, MA 02138, USA
Oxford OX1 3QD, UK
George Chalhoub studies the security, privacy, and safety of AI systems, from large language models to autonomous AI agents. His research brings together human–computer interaction, cybersecurity, and law to understand how people trust and delegate to AI, where these systems break down, and which safeguards make them safer and more accountable.
He holds a DPhil (PhD) in Cyber Security from the University of Oxford, where he was also a postdoctoral researcher, and previously held research roles at Microsoft Research and Nokia Bell Labs. He was endorsed by UK Research and Innovation as a Global Talent, and was a Fellow at Harvard's Berkman Klein Center before becoming a Faculty Associate. His research appears at the top venues in human–computer interaction and security, including ACM CHI, ACM CSCW, USENIX SOUPS, and ACM IMWUT, and he is a named inventor on a US patent with Microsoft.
His research and expert commentary have been featured in Fortune, Yahoo News, the Times of India, Times Higher Education, and outlets across Europe, Asia, and South America.
Research areas
- AI agents. Security risks when autonomous agents act on the web, hold credentials, and coordinate with one another.
- AI browsers and prompt injection. How AI-powered browsers blur the line between data and instructions, and how to protect users.
- Privacy in LLMs. Prompt disclosure, unintended data exposure, and model exploitation in healthcare, law, and journalism.
- AI governance. Regulation, platform policy, and oversight for accountable AI, including its use in science and peer review.
- Human-centred security. How people understand and trust AI systems, and how design can keep them safe.