Mary Maller and Daniel Benarroch | Never trust an agent: identity and permissions for digital and embodied AI
Foresight Institute’s Computation Group
Never trust an agent: identity and permissions for digital and embodied AI
Abstract: For the ARIA discovery program, we investigated the challenges in connecting embodied AI to digital services. Embodied AI systems increasingly interact with external digital services yet each domain has evolved its identity and security infrastructure in isolation. This work asked what additional infrastructure is required to connect them safely.
More broadly, the Inversed team have been working on secure identity and permissions in the context of agentic systems. With Foresight we are building an identity platform for the agentic age. This project aims to design and prototype an identity system and novel cryptographic technologies for a multi-agent world, addressing core challenges in AI agentic security, fine-grained authorization and accountability, secure data access, and data protection in multi-agent communication.
Speakers Bio:
Mary Maller: Cryptographer at Inversed Tech, with a PhD from University College London. Project lead for ARIA preprogram grant on identity for embodied AI. Formerly led cryptography research team at Ethereum Foundation and designed post-quantum threshold signatures at PQShield, bridging deep theory with practical systems.
Daniel Benarroch: CEO and Co-Founder of Inversed Tech. With over a decade in cryptography, Daniel founded zkproof.org and the Crypto Lounge Experience. He combines technical vision with conscious leadership.
Inversed is an R&D studio specialized in secure and verifiable computation. Our team has delivered production-grade systems spanning privacy-preserving biometrics, where we designed and scaled a large-scale identity database secured end-to-end with multi-party computation, to advanced cryptographic infrastructure including zero-knowledge virtual machines, private blockchain asset transfers, and differential privacy frameworks for sensitive consumer data. Across these efforts, we combine deep cryptographic research with practical systems engineering to turn frontier techniques—MPC, ZKPs, and distributed algorithms—into deployable infrastructure that enables accountability, privacy, and control in increasingly autonomous and data-driven environments. https://www.inversed.tech/
A group of scientists, engineers, and entrepreneurs in computer science, ML, cryptography, and related fields who leverage those technologies to improve voluntary cooperation across humans, and ultimately AIs.
Subscribe to our newsletter
Nominate a seminar presenter/topic
Share this application with colleagues who’d like to join
Our book Gaming the Future: Technologies for Intelligent Voluntary Cooperation is now online on Substack.
Zoom link: https://us02web.zoom.us/j/81623367983