TIDES Lab
Trustworthy Intelligence in Distributed and Edge Systems
Department of Computer Engineering and Computer Science
California State University, Long Beach
We study how to make machine learning trustworthy when it runs across many parties and devices that cannot all be trusted. Our current focus is zero-knowledge and post-quantum methods for federated, decentralized, and edge learning.
Research
Verifiable and post-quantum federated learning
Federated learning that can prove its results with zero-knowledge proofs and stays secure against quantum-capable attackers, including models trained across institutions that cannot share raw data.
- ZKP-FedEval: Verifiable and privacy-preserving federated evaluation using zero-knowledge proofs arXiv preprint, 2025
- PQS-BFL: A post-quantum secure blockchain-based federated learning framework Expert Systems with Applications, 2026
- FedGraph-VASP: Privacy-preserving federated graph learning with post-quantum security for cross-institutional anti-money laundering arXiv preprint, 2026
Resilience to malicious and strategic participants
Mechanisms that make poisoning and free-riding unprofitable in collaborative learning, and decoys that raise the cost of attacking device networks.
- A Bayesian incentive mechanism for poison-resilient federated learning arXiv preprint, 2025
- Blockchain-enabled dynamic honeypot conversion for resource-efficient IoT security Journal of Information Security and Applications, 2025
Cryptographic assurance at the edge
Hardware fingerprints and zero-knowledge proofs that let constrained devices show they are genuine and trustworthy, with cryptography light enough to run on them.
- PUFZIN: Secure and scalable blockchain-IoT with PUFs and zero-knowledge proofs Journal of Information Security and Applications, 2026
- Performance analysis and deployment considerations of post-quantum cryptography for consumer electronics arXiv preprint, 2025
Full publication list on Google Scholar.
People
Daniel Commey, Director. Assistant Professor of Cybersecurity, California State University, Long Beach.
The lab is recruiting CSULB undergraduate and MS students. How to join.
Contact
For research collaboration, email daniel.commey@csulb.edu. Prospective students should use the interest form instead of email.