Daniel Commey
Incoming Assistant Professor of Cybersecurity
Computer Engineering & Computer Science, California State University, Long Beach
I am an incoming Assistant Professor of Cybersecurity at California State University, Long Beach, starting August 17, 2026. I work on the security and privacy of distributed and federated AI: systems that have to keep working even when some of the devices, data, or participants can't be trusted. Right now I focus on zero-knowledge and post-quantum methods for federated, decentralized, and edge learning. I also use incentive design to make these systems more reliable when participants misbehave.
Current threads: checking that federated and decentralized learning works as claimed; preparing these systems for quantum threats; defending against participants who poison or game the system; and building lightweight security for IoT and edge devices.
Students
Starting in Fall 2026, I will work with CSULB undergraduate and MS students through the TIDES Lab. If you are a CSULB student interested in trustworthy systems, see how to join.
News
- June 2026. I accepted a position as Assistant Professor of Cybersecurity at California State University, Long Beach. I will join CSULB in Fall 2026.
- June 2026. I passed the CompTIA Cybersecurity Analyst (CySA+) certification.
- May 2026. Our PUFZIN paper was published in the Journal of Information Security and Applications. It combines PUFs and zero-knowledge proofs for secure and scalable blockchain-IoT authentication.
- May 2026. I completed my Ph.D. in Interdisciplinary Engineering at Texas A&M University. My dissertation is titled "A Layered Security Framework for Blockchain-Based IoT Systems."
- May 2026. Two of our papers appeared at IEEE ICC 2026 and IEEE ICC Workshops 2026. They cover AIS dropout attribution and the reliability of production Layer-2 networks.
Selected Publications
ZKP-FedEval: Verifiable and Privacy-Preserving Federated Evaluation using Zero-Knowledge Proofs
Daniel Commey, B. Appiah, G. S. Klogo, G. V. Crosby
arXiv:2507.11649 [cs.LG], 2025
TL;DR Replaces raw metric reporting in federated learning with a zero-knowledge proof of a predicate (for example, loss below a threshold), so the server can gate updates without learning the actual metric.
PQS-BFL: A Post-Quantum Secure Blockchain-based Federated Learning Framework
Daniel Commey, G. V. Crosby
Expert Systems with Applications, 2026
TL;DR A post-quantum-secure, blockchain-verified federated learning framework that keeps model updates authenticated against quantum adversaries.
FedGraph-VASP: Privacy-Preserving Federated Graph Learning with Post-Quantum Security for Cross-Institutional Anti-Money Laundering
Daniel Commey, M. Nkoom, Y. Alsenani, S. G. Hounsinou, G. V. Crosby
arXiv:2601.17935 [cs.LG], 2026
TL;DR Detects cross-institution money laundering by sharing only boundary node embeddings (never raw transaction graphs) through federated graph learning, secured with post-quantum cryptography.
Post-Quantum Secure Blockchain-Based Federated Learning Framework for Healthcare Analytics
Daniel Commey, S. G. Hounsinou, G. V. Crosby
IEEE Networking Letters, 2025
TL;DR A post-quantum, blockchain-verified federated learning framework tailored to privacy-sensitive healthcare analytics.
PUFZIN: Secure and Scalable Blockchain-IoT with PUFs and Zero-Knowledge Proofs
Daniel Commey, S. G. Hounsinou, G. V. Crosby
Journal of Information Security and Applications, vol. 100, article 104510, 2026
TL;DR Combines physical-unclonable-function device fingerprints with zero-knowledge proofs for scalable, privacy-preserving authentication in blockchain-IoT.
Blockchain-Enabled Dynamic Honeypot Conversion for Resource-Efficient IoT Security
Daniel Commey, M. Nkoom, S. G. Hounsinou, G. V. Crosby
Journal of Information Security and Applications, 2025
TL;DR Dynamically converts idle IoT devices into honeypots using ML threat scoring and game theory, improving security with minimal resource cost.