Hidde Lycklama
I am a fourth-year Ph.D. student at the Privacy Preserving Systems Lab. My research focuses on the robustness and accountability of secure (collaborative) learning systems. My goal is to design systems that balance privacy and transparency through the application of cryptography such as zero-knowledge proofs and secure multi-party computation, based on a rigorous understanding of learning systems' integrity issues. I completed my M.Sc. degree at ETH Zurich in Computer Science. Before that, I graduated cum laude with honors at the Delft University of Technology with a B.Sc in Computer Science.
Talks
Holding Secrets Accountable: Auditing Private ML Algorithms
- USENIX Security 2024, Philadelphia, August 2024
- Berkeley Security Seminar, March 2024
- Stanford Security Lunch, March 2024
- ETH Zurich Systems Lunch Seminar, Fall 2023
RoFL: Robustness of Secure Federated Learning
- Systems Group Industry Retreat, 2024
- IEEE S&P 2023, San Francisco, [Video]
- ETH Zurich Systems Lunch Seminar, Spring 2023
Camel: Collaborative Audits for Machine Learning
- ML Safety Workshop at NeurIPS 2022
- USENIX Security 2022, Boston: Poster Session
Teaching
- Data Structures and Algorithms (2024SS)
- Advanced Operating Systems (2022SS, 2023SS)
- Computer Systems (2021FS, 2022FS, 2023FS, 2024FS)
- Computer Science for ITET (2021SS)
Publications
Artemis: Efficient Commit-and-Prove SNARKs for zkML Paper Github
Hidde Lycklama*, Alexander Viand*, Nikolay Avramov, Nicolas Küchler, Anwar Hithnawi
Preprint, arXiv:2409.12055
UTrace: Poisoning Forensics for Private Collaborative Learning Paper
Evan Rose, Hidde Lycklama, Harsh Chaudhari, Anwar Hithnawi, Alina Oprea
Preprint, arXiv:2409.15126
Holding Secrets Accountable: Auditing Privacy-Preserving Machine Learning Paper Slides Github Video
Hidde Lycklama, Alexander Viand, Nicolas Küchler, Christian Knabenhans, Anwar Hithnawi
USENIX Security 2024.
Cohere: Managing Differential Privacy in Large Scale Systems Paper Slides Github Video
Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi
IEEE Security and Privacy (Oakland) 2024.
RoFL: Robustness of Secure Federated Learning Paper Slides Github Video
Hidde Lycklama*, Lukas Burkhalter*, Alexander Viand, Nicolas Küchler, Anwar Hithnawi
IEEE Security and Privacy (Oakland) 2023.
Cryptographic Auditing for Collaborative Learning Paper Poster
Hidde Lycklama, Nicolas Küchler, Alexander Viand, Emanuel Opel, Lukas Burkhalter, Anwar Hithnawi
ML Safety Workshop at NeurIPS 2022
Decreg: A framework for preventing double-financing using blockchain technology Paper
Hidde Lycklama, Joris Oudejans, Zekeriya Erkin
ACM Workshop on Blockchain, Cryptocurrencies and Contracts 2017. Abu Dhabi.