{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:11:44Z","timestamp":1791994304808,"version":"4.4.0"},"reference-count":40,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"SAINT JEAN INGENIEUR"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT) is enabling a new class of intelligent applications. Specifically, Large Language Models (LLMs) are emerging as powerful tools not only for natural language understanding but also for enhancing IoT security. However, the integration of these computationally intensive models into resource-constrained IoT environments presents significant challenges. This paper provides an in-depth examination of how LLMs can be adapted to secure IoT ecosystems. We identify key application areas, discuss major challenges, and propose optimization strategies for resource-limited settings. Our primary contribution is a novel collaborative embeddings offloading mechanism for IoT intrusion detection named SEED (Semantic Embeddings for Efficient Detection). This system leverages a lightweight, fine-tuned BERT model, chosen for its proven contextual and semantic understanding of sequences, to generate rich network embeddings at the edge. A compact neural network deployed on the end-device then queries these embeddings to assess network flow normality. This architecture alleviates the computational burden of running a full transformer on the device while capitalizing on its analytical performance. Our optimized BERT model is reduced by approximately 90% from its original size, now representing approximately 41 MB, suitable for the Edge. The resulting compact neural network is a mere 137 KB, appropriate for the IoT devices. This system achieves 99.9% detection accuracy with an average inference time of under 70 ms on a standard CPU. Finally, the paper discusses the ethical implications of LLM-IoT integration and evaluates the resilience of LLMs in dynamic and adversarial environments.<\/jats:p>","DOI":"10.3390\/s26020356","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T11:13:18Z","timestamp":1767697998000},"page":"356","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["From Edge Transformer to IoT Decisions: Offloaded Embeddings for Lightweight Intrusion Detection"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3051-4280","authenticated-orcid":false,"given":"Fr\u00e9d\u00e9ric","family":"Adjewa","sequence":"first","affiliation":[{"name":"LIST3N, University of Technology of Troyes, 12 rue Marie Curie, 10010 Troyes CEDEX, France"},{"name":"Computer Science Departement, Saint Jean Ing\u00e9nieur, Yaounde 749, Cameroon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moez","family":"Esseghir","sequence":"additional","affiliation":[{"name":"LIST3N, University of Technology of Troyes, 12 rue Marie Curie, 10010 Troyes CEDEX, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le\u00efla","family":"Merghem-Boulahia","sequence":"additional","affiliation":[{"name":"LIST3N, University of Technology of Troyes, 12 rue Marie Curie, 10010 Troyes CEDEX, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Gad, M.M., Gad, W., Abdelkader, T., and Naik, K. (2025). Personalized Smart Home Automation Using Machine Learning: Predicting User Activities. Sensors, 25.","DOI":"10.3390\/s25196082"},{"key":"ref_2","first-page":"100291","article-title":"Wearable IoT (w-IoT) artificial intelligence (AI) solution for sustainable smart-healthcare","volume":"5","author":"Singh","year":"2025","journal-title":"Int. J. Inf. Manag. Data Insights"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Alfahaid, A., Alalwany, E., Almars, A.M., Alharbi, F., Atlam, E., and Mahgoub, I. (2025). Machine Learning-Based Security Solutions for IoT Networks: A Comprehensive Survey. Sensors, 25.","DOI":"10.3390\/s25113341"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"5504","DOI":"10.1016\/j.egyr.2024.05.021","article-title":"A comprehensive review of advancements in green IoT for smart grids: Paving the path to sustainability","volume":"11","author":"Pandiyan","year":"2024","journal-title":"Energy Rep."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Oranekwu, I., Elluri, L., and Batra, G. (2024, January 15\u201318). Automated Knowledge Framework for IoT Cybersecurity Compliance. Proceedings of the 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA.","DOI":"10.1109\/BigData62323.2024.10825755"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ghimire, A., Ghajari, G., Gurung, K., Sah, L.K., and Amsaad, F. (2025). Enhancing Cybersecurity in Critical Infrastructure with LLM-Assisted Explainable IoT Systems. arXiv.","DOI":"10.1109\/SATC65530.2025.11137104"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kasri, W., Himeur, Y., Alkhazaleh, H.A., Tarapiah, S., Atalla, S., Mansoor, W., and Al-Ahmad, H. (2025). From Vulnerability to Defense: The Role of Large Language Models in Enhancing Cybersecurity. Computation, 13.","DOI":"10.3390\/computation13020030"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"176751","DOI":"10.1109\/ACCESS.2024.3505983","article-title":"Application of Large Language Models in Cybersecurity: A Systematic Literature Review","volume":"12","author":"Hasanov","year":"2024","journal-title":"IEEE Access"},{"key":"ref_9","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"23733","DOI":"10.1109\/ACCESS.2024.3363469","article-title":"Revolutionizing cyber threat detection with large language models: A privacy-preserving bert-based lightweight model for iot\/iiot devices","volume":"12","author":"Ferrag","year":"2024","journal-title":"IEEE Access"},{"key":"ref_11","first-page":"778","article-title":"Efficient prompting for llm-based generative internet of things","volume":"12","author":"Xiao","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_12","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Association for Computational Linguistics."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Alshattnawi, S., Shatnawi, A., AlSobeh, A.M., and Magableh, A.A. (2024). Beyond word-based model embeddings: Contextualized representations for enhanced social media spam detection. Appl. Sci., 14.","DOI":"10.3390\/app14062254"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"57128","DOI":"10.1109\/ACCESS.2024.3382709","article-title":"A survey on security, privacy, trust, and architectural challenges in IoT systems","volume":"12","author":"Adam","year":"2024","journal-title":"IEEE Access"},{"key":"ref_15","unstructured":"Mo, S., Salakhutdinov, R., Morency, L.P., and Liang, P.P. (2024). Iot-lm: Large multisensory language models for the internet of things. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"102397","DOI":"10.1016\/j.jocs.2024.102397","article-title":"Exploring the integration of IoT and Generative AI in English language education: Smart tools for personalized learning experiences","volume":"82","author":"Dong","year":"2024","journal-title":"J. Comput. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1007\/s43926-024-00083-4","article-title":"Integrating large language models with internet of things: Applications","volume":"5","author":"Zong","year":"2025","journal-title":"Discov. Internet Things"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Omar, M., Zangana, H.M., Al-Karaki, J.N., and Mohammed, D. (2024, January 7\u20139). Harnessing LLMs for IoT Malware Detection: A Comparative Analysis of BERT and GPT-2. Proceedings of the 2024 8th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Ankara, Turkiye.","DOI":"10.1109\/ISMSIT63511.2024.10757249"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Sharafaldin, I., Lashkari, A.H., and Ghorbani, A.A. (2018, January 22\u201324). Toward generating a new intrusion detection dataset and intrusion traffic characterization. Proceedings of the 4th International Conference on Information Systems Security and Privacy\u2014ICISSP, Funchal, Portugal.","DOI":"10.5220\/0006639801080116"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tavallaee, M., Bagheri, E., Lu, W., and Ghorbani, A.A. (2009, January 8\u201310). A detailed analysis of the KDD CUP 99 data set. Proceedings of the 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, Ottawa, ON, Canada.","DOI":"10.1109\/CISDA.2009.5356528"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Diaf, A., Korba, A.A., Karabadji, N.E., and Ghamri-Doudane, Y. (2025). BARTPredict: Empowering IoT Security with LLM-Driven Cyber Threat Prediction. arXiv.","DOI":"10.1109\/GLOBECOM52923.2024.10901770"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Neto, E.C.P., Dadkhah, S., Ferreira, R., Zohourian, A., Lu, R., and Ghorbani, A.A. (2023). CICIoT2023: A real-time dataset and benchmark for large-scale attacks in IoT environment. Sensors, 23.","DOI":"10.20944\/preprints202305.0443.v1"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Adjewa, F., Esseghir, M., and Merghem-Boulahia, L. (2024, January 21\u201323). Efficient federated intrusion detection in 5g ecosystem using optimized bert-based model. Proceedings of the 2024 20th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Paris, France.","DOI":"10.1109\/WiMob61911.2024.10770340"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Zhang, J., Bu, H., Wen, H., Liu, Y., Fei, H., Xi, R., Li, L., Yang, Y., Zhu, H., and Meng, D. (2024). When LLMs meet cybersecurity: A systematic literature review. arXiv.","DOI":"10.1186\/s42400-025-00361-w"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1109\/TSE.2025.3548168","article-title":"SecureFalcon: Are we there yet in automated software vulnerability detection with LLMs?","volume":"51","author":"Ferrag","year":"2025","journal-title":"IEEE Trans. Softw. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Hang, C.N., Yu, P.D., Morabito, R., and Tan, C.W. (2024). Large language models meet next-generation networking technologies: A review. Future Internet, 16.","DOI":"10.3390\/fi16100365"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, M., Yang, N., and Weng, N. (2023). Securing a smart home with a transformer-based IoT intrusion detection system. Electronics, 12.","DOI":"10.3390\/electronics12092100"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"McDonald, D., Papadopoulos, R., and Benningfield, L. (Authorea, 2024). Reducing llm hallucination using knowledge distillation: A case study with mistral large and mmlu benchmark, Authorea, preprints.","DOI":"10.36227\/techrxiv.171665607.76504195\/v1"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"K\u00f6k, \u0130., Demirci, O., and \u00d6zdemir, S. (2024, January 15\u201318). When IoT Meet LLMs: Applications and Challenges. Proceedings of the 2024 IEEE International Conference on Big Data (BigData), Washington, DC, USA.","DOI":"10.1109\/BigData62323.2024.10825187"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Yu, Z., Wang, Z., Li, Y., Gao, R., Zhou, X., Bommu, S.R., Zhao, Y., and Lin, Y. (2024, January 23\u201327). Edge-llm: Enabling efficient large language model adaptation on edge devices via unified compression and adaptive layer voting. Proceedings of the 61st ACM\/IEEE Design Automation Conference, San Francisco CA USA.","DOI":"10.1145\/3649329.3658473"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhao, W., Jing, W., Lu, Z., and Wen, X. (2024, January 7\u20139). Edge and terminal cooperation enabled llm deployment optimization in wireless network. Proceedings of the 2024 IEEE\/CIC International Conference on Communications in China (ICCC Workshops), Hangzhou, China.","DOI":"10.1109\/ICCCWorkshops62562.2024.10693742"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3820","DOI":"10.1109\/COMST.2025.3527641","article-title":"Mobile edge intelligence for large language models: A contemporary survey","volume":"27","author":"Qu","year":"2025","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Deshmukh, A., de la Rosa, P.E., Rodriguez, R.V., and Dasari, S. (2025). Enhancing Privacy in IoT-Enabled Digital Infrastructure: Evaluating Federated Learning for Intrusion and Fraud Detection. Sensors, 25.","DOI":"10.3390\/s25103043"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"40281","DOI":"10.1109\/ACCESS.2022.3165809","article-title":"Edge-IIoTset: A new comprehensive realistic cyber security dataset of IoT and IIoT applications for centralized and federated learning","volume":"10","author":"Ferrag","year":"2022","journal-title":"IEEE Access"},{"key":"ref_35","unstructured":"Kumar, A., Murthy, S.V., Singh, S., and Ragupathy, S. (2024). The ethics of interaction: Mitigating security threats in llms. arXiv."},{"key":"ref_36","unstructured":"Gan, Y., Yang, Y., Ma, Z., He, P., Zeng, R., Wang, Y., Li, Q., Zhou, C., Li, S., and Wang, T. (2024). Navigating the risks: A survey of security, privacy, and ethics threats in llm-based agents. arXiv."},{"key":"ref_37","unstructured":"Liu, Y., Cong, T., Zhao, Z., Backes, M., Shen, Y., and Zhang, Y. (2023). Robustness Over Time: Understanding Adversarial Examples\u2019 Effectiveness on Longitudinal Versions of Large Language Models. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Che, X., Li, H., Chi, L., Wang, F., and Hu, J. (2023). Evaluation the Robustness of Iot Intrusion Detection Models in Adversarial Attack Environments. SSRN, 4611920.","DOI":"10.2139\/ssrn.4611920"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Khaleel, T.A. (2024, January 23\u201325). Developing robust machine learning models to defend against adversarial attacks in the field of cybersecurity. Proceedings of the 2024 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Istanbul, Turkiye.","DOI":"10.1109\/HORA61326.2024.10550799"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Fan, X., and Tao, C. (2024). Towards resilient and efficient llms: A comparative study of efficiency, performance, and adversarial robustness. arXiv.","DOI":"10.1145\/3719384.3719447"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/356\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T11:16:47Z","timestamp":1767698207000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/356"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":40,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020356"],"URL":"https:\/\/doi.org\/10.3390\/s26020356","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]}}}