Mrs. M. Gomathi, S. Sowndharya

DOI: https://doi.org/10.5281/zenodo.23594801

Internet of Things (IoT) devices now run in factories, hospitals, buildings and other critical infrastructure, so the security of their communication matters more every year. Most deployments protect keys and identities with RSA or elliptic-curve cryptography (ECC), which a large fault-tolerant quantum computer could break. At the same time, IoT networks are exposed to everyday attacks such as denial of service, port scanning and spoofing. In practice, cryptographic protection and intrusion detection are built as two unrelated pieces. This paper proposes a framework that studies them together. It pairs the NIST post-quantum standards ML-KEM (key establishment) and ML-DSA (digital signatures) with a Random Forest classifier and a Long Short-Term Memory (LSTM) network for traffic analysis. An ESP32-class edge device, MQTT messaging, a signed event log and a monitoring dashboard complete the design. We describe the problem, the research gap, the architecture and the evaluation plan. The prototype is still to be built, so no measured results are reported.

Internet of Things, post-quantum cryptography, ML-KEM, ML-DSA, ESP32, MQTT, intrusion detection, Random Forest, LSTM.

This paper proposed a coordinated IoT security design that addresses both the future risk to public-key cryptography and the network threats of today. It combines the NIST standards ML-KEM and ML-DSA, MQTT communication and Random Forest and LSTM intrusion detection. The literature review showed that integration, resource profiling, reproducible evaluation and clear protocol boundaries remain open issues. The modular architecture allows staged development and independent testing of each component. All performance values in this paper are planned targets for evaluation, not experimental findings.

National Institute of Standards and Technology, “Module-Lattice-Based Key-Encapsulation Mechanism Standard,” FIPS 203, Aug. 2024, doi: 10.6028/NIST.FIPS.203.
[2] National Institute of Standards and Technology, “Module-Lattice-Based Digital Signature Standard,” FIPS 204, Aug. 2024, doi: 10.6028/NIST.FIPS.204.
[3] National Institute of Standards and Technology, “Stateless Hash-Based Digital Signature Standard,” FIPS 205, Aug. 2024, doi: 10.6028/NIST.FIPS.205.
[4] P. W. Shor, “Algorithms for quantum computation: Discrete logarithms and factoring,” in Proc. 35th Annu. Symp. Found. Comput. Sci. (FOCS), 1994, pp. 124–134, doi: 10.1109/SFCS.1994.365700.
[5] E. Barker, “Recommendation for key management: Part 1 – General,” NIST Spec. Publ. 800-57 Part 1 Rev. 5, May 2020, doi: 10.6028/NIST.SP.800-57pt1r5.
[6] M. J. Kannwischer, J. Rijneveld, P. Schwabe, and K. Stoffelen, “PQM4: Testing and benchmarking NIST PQC on ARM Cortex-M4,” in Proc. 8th ACM ASIA Public-Key Cryptography Workshop, 2021.
[7] I. Sharafaldin, A. H. Lashkari, and A. A. Ghorbani, “Toward generating a new intrusion detection dataset and intrusion traffic characterization,” in Proc. ICISSP, 2018, pp. 108–116, doi: 10.5220/0006639801080116.
[8] N. Moustafa and J. Slay, “UNSW-NB15: A comprehensive data set for network intrusion detection systems,” in Proc. Mil. Commun. Inf. Syst. Conf. (MilCIS), 2015, pp. 1–6, doi: 10.1109/MilCIS.2015.7348942.
[9] OASIS, “MQTT Version 5.0,” OASIS Standard, Mar. 2019.
[10] National Institute of Standards and Technology, “Post-Quantum Cryptography,” NIST Computer Security Resource Center. [Online]. Available: https://csrc.nist.gov/projects/post-quantum-cryptography
[11] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 10.1162/neco.1997.9.8.1735. 8, pp. 1735–1780, 1997, doi:
[12] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
[13] NIST, “Guidelines for the selection, configuration, and use of Transport Layer Security (TLS) implementations,” NIST Spec. Publ. 800-52 Rev. 2, Aug. 2019, doi: 10.6028/NIST.SP.800-52r2

Mrs. M. Gomathi, S. Sowndharya (2026). AI-Driven Quantum-Safe IoT Security Framework for Real-Time Threat Detection. International Journal of Computer Science Engineering Techniques, 10(5), 413–417. ISSN: 2455-135X. DOI: https://doi.org/10.5281/zenodo.23594801