Privacy Preserving Systems Lab
At the Privacy-Preserving Systems Lab, we build practical systems that enable computation on sensitive data without exposing it. We focus on making privacy-enabling technologies such as homomorphic encryption, secure multi-party computation, and zero-knowledge proofs efficient, scalable, and accessible.
Much of our current work focuses on the security and accountability of AI systems. We develop methods to securely audit and verify machine learning pipelines, establish trustworthy data provenance, and address security challenges in emerging agentic AI systems. Our broader goal is to make strong privacy, security, and accountability guarantees practical for real-world systems.
The Privacy-Preserving Systems Lab is based in the Department of Computer Science at the University of Toronto and is led by Prof. Anwar Hithnawi.
Projects
Recent Blogs
All postsNews
All news- Anwar received the Google Research Scholar Award!
- Anwar received the Intel Outstanding Researcher Award!
Publications
Ashwin Karthikeyan*, Ethan Kharitonov*, Kuldeep S. Meel, Anwar Hithnawi
Conference on Logic for Programming, Artificial Intelligence, and Reasoning (LPAR 2026)
Nikolay Avramov, Hidde Lycklama, Alexander Viand, Anwar Hithnawi
Preprint, arXiv:2609.11841
Ashwin Karthikeyan, Hengyu Liu, Kuldeep S. Meel, Ning Luo
IEEE Security and Privacy (Oakland) 2026.
Asra Ali, Jaeho Choi, Bryant Gipson, Shruthi Gorantala, Jeremy Kun, Wouter Legiest, Lawrence Lim, Alexander Viand, Meron Zerihun Demissie, Hongren Zheng
Preprint, arXiv:2508.11095
DPolicy: Managing Privacy Risks Across Multiple Releases with Differential Privacy
Paper Slides GithubNicolas Küchler, Alexander Viand, Hidde Lycklama, Anwar Hithnawi
IEEE Security and Privacy (Oakland) 2025.
Roberta De Viti, Isaac Sheff, Noemi Glaeser, Baltasar Dinis, Rodrigo Rodrigues, Bobby Bhattacharjee, Anwar Hithnawi, Deepak Garg, Peter Druschel
USENIX Security 2025.
Hidde Lycklama*, Alexander Viand*, Nikolay Avramov, Nicolas Küchler, Anwar Hithnawi
Preprint, arXiv:2409.12055
Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi
IEEE Security and Privacy (Oakland) 2024.
Christian Knabenhans*, Alexander Viand*, Antonio Merino-Gallardo, Anwar Hithnawi
Workshop on Encrypted Computing & Applied Homomorphic Cryptography (WAHC '24)
Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi
IEEE Security and Privacy (Oakland) 2023.
VF-PS: How to Select Important Participants in Vertical Federated Learning, Efficiently and Securely?.
PaperJiawei Jiang, Lukas Burkhalter, Fangcheng Fu, Bolin Ding, Bo Du, Anwar Hithnawi, Bo Li, Ce Zhang
NeurIPS (Spotlight) 2022.
Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi
ML Safety Workshop at NeurIPS 2022
Lukas Burkhalter*, Nicolas Küchler*, Alexander Viand, Hossein Shafagh, Anwar Hithnawi
USENIX OSDI 2021.
Alexander Viand, Patrick Jattke, Anwar Hithnawi
IEEE Security and Privacy (Oakland) 2021.
Droplet: Decentralized Authorization and Access Control for Encrypted Data Streams.
Paper Slides Github Website VideoHossein Shafagh, Lukas Burkhalter, Sylvia Ratnasamy, Anwar Hithnawi
USENIX Security 2020.
TimeCrypt: Encrypted Data Stream Processing at Scale with Cryptographic Access Control.
Paper Slides Github Website VideoLukas Burkhalter, Anwar Hithnawi, Alexander Viand, Hossein Shafagh, Sylvia Ratnasamy
USENIX NSDI 2020.