Implementation of the ML-KEM Protocol for Securing Parameter Exchange in FedAvg-Based Federated Learning Architecture Against Quantum Computing Threats

Ariq Arsalan; Eko Hari Rachmawanto; Christy Atika Sari

doi:10.30871/jaic.v10i4.13589

Authors

Ariq Arsalan Universitas Dian Nuswantoro
Eko Hari Rachmawanto Universitas Dian Nuswantoro
Christy Atika Sari Universitas Dian Nuswantoro

DOI:

https://doi.org/10.30871/jaic.v10i4.13589

Keywords:

Federated Learning, ML-KEM, Post-Quantum Cryptography, FedAvg, Lattice-based Cryptography

Abstract

Federated Learning (FL) enables collaborative machine learning by aggregating local models from decentralized clients without sharing raw data. However, the parameter exchange process in standard FL architectures is vulnerable to emerging quantum computing threats. Specifically, Shor's algorithm, executable on large-scale quantum computers, can break conventional asymmetric cryptography such as RSA and ECDH in polynomial time, thereby threatening the security of FL systems that rely on these traditional public-key infrastructures for parameter exchange. This study addresses this vulnerability by implementing the recently standardized post-quantum cryptographic protocol, ML-KEM (Module-Lattice-Based Key-Encapsulation Mechanism), within a FedAvg-based FL architecture. The integration is designed to secure the parameter exchange pipeline without compromising the neural network's performance. Experimental results on a simulated environment utilizing the MNIST dataset demonstrate that the ML-KEM integration preserves 100% of the global model accuracy. Furthermore, the cryptographic latency overhead introduced by encapsulation and decapsulation remains highly efficient, proving its potential as a robust security layer. While current evaluations focus on small-scale deployments, the proposed architecture establishes a foundational post-quantum security framework for future privacy-preserving distributed learning systems.

Downloads

Download data is not yet available.

Author Biographies

Eko Hari Rachmawanto, Universitas Dian Nuswantoro

SciProfiles: 3820122 ResearcherID: AEM-9575-2022 Scopus Author ID: 57193850466

Christy Atika Sari, Universitas Dian Nuswantoro

Scopus Author ID: 57193848115 SciProfiles: 3076319 ResearcherID: ACO-2038-2022

References

[1] P. Nayak, G. Thiyagarajan, R. Mishra, and V. Bist, “Post-Quantum Federated Learning: Secure And Scalable Threat Intelligence For Collaborative Cyber Defense”.

[2] H. GHaravi, J. Granjal, and E. Monteiro, “PQBFL: A Post-Quantum Blockchain-based Protocol for Federated Learning,” Feb. 20, 2025, arXiv: arXiv:2502.14464. doi: 10.48550/arXiv.2502.14464.

[3] A. Alshammari, “Energy-Efficient Cryptographic Protocols for Sustainable IoT Security: A Federated Learning-Enhanced Lightweight Framework with Post-Quantum Resilience,” Sensors, vol. 26, no. 12, p. 3656, Jun. 2026, doi: 10.3390/s26123656.

[4] D. Commey and G. V. Crosby, “PQS-BFL: A Post-Quantum Secure Blockchain-based Federated Learning Framework,” Expert Syst. Appl., vol. 312, p. 131449, May 2026, doi: 10.1016/j.eswa.2026.131449.

[5] P. Li, T. Chen, and J. Liu, “Enhancing Quantum Security over Federated Learning via Post-Quantum Cryptography,” in 2024 IEEE 6th International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA), Oct. 2024, pp. 499–505. doi: 10.1109/TPS-ISA62245.2024.00067.

[6] E. Lansiaux, “Zero-Knowledge Federated Learning with Lattice-Based Hybrid Encryption for Quantum-Resilient Medical AI,” Mar. 03, 2026, arXiv: arXiv:2603.03398. doi: 10.48550/arXiv.2603.03398.

[7] C. B. Şahin, “Quantum-Resilient Federated Learning for Multi-Layer Cyber Anomaly Detection in UAV Systems,” Sensors, vol. 26, no. 2, p. 509, Jan. 2026, doi: 10.3390/s26020509.

[8] E. Hosseini, S. Chen, and A. Khisti, “Secure Aggregation in Federated Learning using Multiparty Homomorphic Encryption,” Mar. 01, 2025, arXiv: arXiv:2503.00581. doi: 10.48550/arXiv.2503.00581.

[9] G. Yan, S. Lyu, H. Hou, Z. Zheng, and L. Song, “Towards Quantum-Safe Federated Learning via Homomorphic Encryption: Learning with Gradients,” Feb. 02, 2024, arXiv: arXiv:2402.01154. doi: 10.48550/arXiv.2402.01154.

[10] S. Bitzer, M. Egger, M. Liu, and A. Wachter-Zeh, “Post-Quantum Secure Aggregation via Code-Based Homomorphic Encryption,” Jan. 19, 2026, arXiv: arXiv:2601.13031. doi: 10.48550/arXiv.2601.13031.

[11] J. S. Buruaga, R. B. Méndez, J. P. Brito, and V. Martin, “Quantum-Safe integration of TLS in SDN networks,” Feb. 24, 2025, arXiv: arXiv:2502.17202. doi: 10.48550/arXiv.2502.17202.

[12] H. Nguyen, S. Huda, Y. Nogami, and T. T. Nguyen, “Security in Post-Quantum Era: A Comprehensive Survey on Lattice-Based Algorithms,” IEEE Access, vol. 13, pp. 89003–89024, 2025, doi: 10.1109/ACCESS.2025.3571307.

[13] C. İnce, “Hybrid ML-KEM in TLS 1.3: Performance Analysis on ARM64 Under Network Stress,” Comput. Sci., no. 2026, Mar. 2026, doi: 10.53070/bbd.1898820.

[14] N. Nagy et al., “Module-Lattice-Based Key-Encapsulation Mechanism Performance Measurements,” Sci, vol. 7, no. 3, p. 91, Jul. 2025, doi: 10.3390/sci7030091.

[15] C.-H. Liu and Z.-Y. Wu, “Quantum-Resistant Secure Aggregation for Healthcare Federated Learning,” Comput. Mater. Contin., vol. 87, no. 2, pp. 1–10, 2026, doi: 10.32604/cmc.2026.075495.

[16] Z.-P. Liu et al., “Experimentally validated quantum-secure federated learning over a multi-user quantum network,” Research, vol. 9, p. 1299, Jan. 2026, doi: 10.34133/research.1299.

[17] C.-H. Liu and Z.-Y. Wu, “Quantum-Resistant Secure Aggregation for Healthcare Federated Learning,” Comput. Mater. Contin., vol. 87, no. 2, pp. 1–10, 2026, doi: 10.32604/cmc.2026.075495.

[18] T. Borger et al., “Federated learning for violence incident prediction in a simulated cross-institutional psychiatric setting,” Expert Syst. Appl., vol. 199, p. 116720, Aug. 2022, doi: 10.1016/j.eswa.2022.116720.

[19] D. S. Venkatesan, D. M. Poonguzhali, V. Ramesh, D. S. T. Revathi, and M. Karthikeyan, “Quantum-Resilient Cryptographic Protocols For Secure Multi- Party Computation In Post-Quantum Networks.,” Lex Localis, vol. 23, 2025.

[20] S. Sachan, D. Fickett, R. Buchinger, and T. Miller, “Post-Quantum Secure Federated DeFi for Inclusive Banking,” in 2026 IEEE Conference on Artificial Intelligence (CAI), Granada, Spain: IEEE, May 2026, pp. 959–964. doi: 10.1109/CAI68641.2026.11536585.

[21] W. Li and D.-L. Deng, “Quantum delegated and federated learning via quantum homomorphic encryption,” Res. Dir. Quantum Technol., vol. 3, p. e3, 2025, doi: 10.1017/qut.2025.2.

[22] S. Dutta et al., “Federated Learning with Quantum Computing and Fully Homomorphic Encryption: A Novel Computing Paradigm Shift in Privacy-Preserving ML,” Oct. 12, 2024, arXiv: arXiv:2409.11430. doi: 10.48550/arXiv.2409.11430.

[23] C. İnce, “Hybrid ML-KEM in TLS 1.3: Performance Analysis on ARM64 Under Network Stress,” Comput. Sci., no. 2026, Mar. 2026, doi: 10.53070/bbd.1898820.

[24] N. Nagy et al., “Module-Lattice-Based Key-Encapsulation Mechanism Performance Measurements,” Sci, vol. 7, no. 3, p. 91, Jul. 2025, doi: 10.3390/sci7030091.

[25] A. Thota and S. Tammisetti, “QGuardian: A Federated Learning Framework for Quantum-Resilient Anomaly Detection in Cybersecurity,” Jan. 12, 2026. doi: 10.36227/techrxiv.176823051.17410568/v1.

[26] R. Chhetri, “Benchmarking NIST-Standardised ML-KEM and ML-DSA on ARM Cortex-M0+: Performance, Memory, and Energy on the RP2040,” 2026, arXiv. doi: 10.48550/ARXIV.2603.19340.

[27] S. Hoque, A. Aydeger, E. Zeydan, and M. Liyanage, “Analysis of Post-Quantum Cryptography in User Equipment in 5G and Beyond,” Jul. 22, 2025, arXiv: arXiv:2507.17074. doi: 10.48550/arXiv.2507.17074.

[28] A. Nath and H. Kasyap, “CQSA: Byzantine-robust Clustered Quantum Secure Aggregation in Federated Learning,” Feb. 25, 2026, arXiv: arXiv:2602.22269. doi: 10.48550/arXiv.2602.22269.