Conferences & lectures

Making AI systems more accountable: New ways to verify compliance

Explore how hardware-assisted security can help verify AI system compliance without exposing sensitive information.

Date & time

Monday, November 23, 2026
9:30 a.m. – 11:15 a.m.

Speaker(s)

N. Asokan

Cost

This event is free.

As artificial intelligence becomes more widely used, governments are introducing regulations to ensure AI systems are fair, trustworthy and accountable. But how can we verify that these systems meet those requirements?

Join us for the Gina Cody School Distinguished Speaker Series, featuring N. Asokan, University Professor at the University of Waterloo.

Asokan will explore new methods for verifying properties of AI systems that can help assess regulatory compliance while protecting sensitive information.

About the talk

Towards auditable properties of AI systems via hardware-assisted attestations

Artificial intelligence (AI) systems are taking the world by storm. Their rapid rise in popularity has led various jurisdictions to formulate policies to regulate the development and use of systems based on AI models ("AI systems" for brevity). These policies are intended to help ensure desirable properties such as equity, fairness and trustworthiness. Given the rapid progress in the AI ecosystem, third parties may need to verify regulatory compliance of a system long before any formal certification. How can we arrange for such verification of relevant properties of AI systems without leaking any sensitive information?

In this talk, I will present our recent work towards this goal. I will describe our frameworks (Laminator and PAL*M), which leverage hardware-assisted trusted execution environments (TEEs) to make it possible to verify various types of properties of a machine learning (ML) pipeline that can be useful for verifying regulatory compliance. I will describe the design and implementation of the frameworks and identify some open problems and questions that require input from regulatory and legal experts in the hope of starting a conversation about what kind of technological mechanisms are needed to facilitate effective regulation of AI systems.

Meet the speaker

N. Asokan is a University Professor at the University of Waterloo. He also serves as a visiting Wallenberg Chair at KTH Royal Institute of Technology. At Waterloo, Asokan held a David R. Cheriton Chair (2019-2025) and served as the Executive Director of the Cybersecurity and Privacy Institute (2021-2025).

Asokan was a Professor of Computer Science at Aalto University from 2013 to 2019, where he was the founding director of the Helsinki-Aalto Institute for Cybersecurity. He was a Professor of Computer Science at the University of Helsinki from 2012 to 2017. Between 1995 and 2012, he worked in industrial research laboratories designing and building secure systems, first at the IBM Zurich Research Laboratoryv as a Research Staff Member and then at Nokia Research Center (NRC), most recently as Distinguished Researcher.

Asokan's primary research theme is systems security broadly, including topics like the development and use of novel platform security features, applying cryptographic techniques to design secure protocols for distributed systems, applying machine learning techniques to security/privacy problems, and understanding/addressing the security and privacy of machine learning applications themselves. Asokan received his doctorate in Computer Science from the University of Waterloo, MS in Computer and Information Science from Syracuse University, and BTech (Hons.) in Computer Science and Engineering from the Indian Institute of Technology at Kharagpur. He is an ACM Fellow, an IEEE Fellow, and a Fellow of the Royal Society of Canada.