{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T06:10:13Z","timestamp":1778652613196,"version":"3.51.4"},"reference-count":50,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T00:00:00Z","timestamp":1769472000000},"content-version":"vor","delay-in-days":26,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Communications"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The rapid growth of 6G Internet of Things (IoT) networks demands scalable and secure learning systems that can support massive device connectivity with minimal coordination overhead. Federated learning (FL) over grant\u2010free non\u2010orthogonal multiple access (GF\u2010NOMA) offers a promising approach by enabling distributed model training with asynchronous uplink access and low signalling cost. However, this setup introduces coupled vulnerabilities: The uncoordinated nature of GF\u2010NOMA leads to random collisions and residual interference, while the decentralised nature of FL exposes the system to poisoning, Sybil and jamming attacks. These cross\u2010layer threats jointly degrade model convergence and communication reliability. To address this, we propose Security\u2010Aware Proximal Policy Optimisation (SA\u2010PPO), a reinforcement learning framework that co\u2010designs communication security for FL over GF\u2010NOMA. SA\u2010PPO jointly embeds physical\u2010layer features (e.g., SINR and interference) and learning\u2010layer signals (e.g., anomaly scores and trust values) into its state, action and reward spaces. This enables the base station to optimise admission control, resource allocation and trust\u2010weighted aggregation in a unified loop. Unlike prior methods that treat communication and security independently, SA\u2010PPO learns coordinated strategies that attenuate adversarial impact while preserving update diversity. Simulation results show that SA\u2010PPO achieves over 90% anomaly detection accuracy, sustains secure participation above 80% and reduces collision\u2010induced decoding errors by 25% under scenarios with up to 40% compromised devices, while incurring only modest increases in energy and latency. These results demonstrate SA\u2010PPO's effectiveness for secure, scalable and resilient edge intelligence in future 6G IoT\u00a0environments.<\/jats:p>","DOI":"10.1049\/cmu2.70138","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T08:18:23Z","timestamp":1769501903000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Communication\u2010Security Co\u2010Design for Federated Learning in Grant\u2010Free NOMA IoT Networks"],"prefix":"10.1049","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8465-5724","authenticated-orcid":false,"given":"Emmanuel","family":"Atebawone","sequence":"first","affiliation":[{"name":"Department of Information Technology University of Professional Studies Accra, Greater Accra Ghana"},{"name":"Department of Telecommunication Engineering Kwame Nkrumah University of Science and Technology Ashanti Region Ghana"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-9950","authenticated-orcid":false,"given":"Kwame Opuni\u2010Boachie Obour","family":"Agyekum","sequence":"additional","affiliation":[{"name":"Department of Telecommunication Engineering Kwame Nkrumah University of Science and Technology Ashanti Region Ghana"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0550-9431","authenticated-orcid":false,"given":"James Dzisi","family":"Gadze","sequence":"additional","affiliation":[{"name":"Department of Telecommunication Engineering Kwame Nkrumah University of Science and Technology Ashanti Region Ghana"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5628-5680","authenticated-orcid":false,"given":"Kwasi Adu\u2010Boahen","family":"Opare","sequence":"additional","affiliation":[{"name":"Department of Telecommunication Engineering Kwame Nkrumah University of Science and Technology Ashanti Region Ghana"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1238-0173","authenticated-orcid":false,"given":"Owusu Agyeman","family":"Antwi","sequence":"additional","affiliation":[{"name":"Department of Telecommunication Engineering Ghana Communication Technology University Greater Accra Ghana"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1428-5697","authenticated-orcid":false,"given":"Robert","family":"Akromond","sequence":"additional","affiliation":[{"name":"Department of Telecommunication Engineering Ghana Communication Technology University Greater Accra Ghana"}]}],"member":"265","published-online":{"date-parts":[[2026,1,27]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"crossref","unstructured":"Y.Wang X.Kang T.Li H.Wang C.\u2010K.Chu andZ.Lei \u201cSix\u2010Trust for 6g: Towards a Secure and Trustworthy 6g Network \u201d preprint arXiv:2210.17291 October 31 2022.","DOI":"10.1109\/ACCESS.2023.3321114"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2300099"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2025.3558672"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2996032"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23198245"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3027158"},{"key":"e_1_2_11_8_1","doi-asserted-by":"crossref","unstructured":"H.Jiang Q.Cui Y.Gu X.Qin X.Zhang andX.Tao \u201cDistributed Layered Grant\u2010Free Non\u2010Orthogonal Multiple Access for Massive MTC \u201d in2018 IEEE 29th Annual International Symposium on Personal Indoor and Mobile Radio Communications (PIMRC)(IEEE 2018) 1\u20137.","DOI":"10.1109\/PIMRC.2018.8580806"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3551759"},{"key":"e_1_2_11_10_1","unstructured":"M.Fayaz W.Yi Y.Liu andA.Nallanathan \u201cA Power\u2010Pool\u2010Based Power Control in Semi\u2010Grant\u2010Free NOMA Transmission \u201dpreprint arXiv:2106.11190(June 21 2021)."},{"key":"e_1_2_11_11_1","doi-asserted-by":"crossref","unstructured":"Z.Yuan Z.Li W.Li Y.Ma andC.Liang \u201cContention\u2010Based Grant\u2010Free Transmission With Extremely Sparse Orthogonal Pilot Scheme \u201d in2021 IEEE 94th Vehicular Technology Conference (VTC2021\u2010Fall)(IEEE 2021) 1\u20136.","DOI":"10.1109\/VTC2021-Fall52928.2021.9625265"},{"key":"e_1_2_11_12_1","unstructured":"A.BaiocchiandA.Razzaque \u201cAsymptotic Analysis of Sum\u2010Rate Under SIC \u201dpreprint arXiv:2405.12937(June 27 2024)."},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/e23111413"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3151193"},{"key":"e_1_2_11_15_1","unstructured":"X.BiandX.Li \u201cSecuring Federated Learning Against Backdoor Threats With Foundation Model Integration \u201dpreprint arXiv:2410.17573(October 23 2024)."},{"key":"e_1_2_11_16_1","unstructured":"Z.Alsulaimawi \u201cSecuring Federated Learning With Control\u2010Flow Attestation: A Novel Framework for Enhanced Integrity and Resilience Against Adversarial Attacks \u201dpreprint arXiv:2403.10005(March 15 2024)."},{"key":"e_1_2_11_17_1","doi-asserted-by":"crossref","unstructured":"C.Feng A. H.Celdr\u00e1n J.Baltensperger E. T. M.Beltr\u00e1n P. M. S.S\u00e1nchez G.Bovet andB.Stiller \u201cSentinel: An Aggregation Function to Secure Decentralized Federated Learning \u201dpreprint arXiv:2310.08097(October 12 2023).","DOI":"10.3233\/FAIA240686"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2024.101079"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2025.3556462"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","unstructured":"Z.Chen Z.Ni P.Guan et\u00a0al. \u201cOptimizing NOMA Transmissions to Advance Federated Learning in Vehicular Networks \u201d inGLOBECOM 2024\u20102024 IEEE Global Communications Conference(IEEE 2024) 962\u2013967.","DOI":"10.1109\/GLOBECOM52923.2024.10901358"},{"key":"e_1_2_11_21_1","unstructured":"P.Sun E.Liu W.Ni K.Yu R.Wang andA.Jamalipour \u201cCluster\u2010Aware Multi\u2010Round Update for Wireless Federated Learning in Heterogeneous Environments \u201dpreprint arXiv:2505.06268(May 6 2025)."},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-03257-4"},{"key":"e_1_2_11_23_1","unstructured":"Z.Jin R.Xu C.Li Y.Liu J.Li andJ.Joshi \u201cSparsification Under Siege: Defending Against Poisoning Attacks in Communication\u2010Efficient Federated Learning \u201dpreprint arXiv:2505.01454(April 30 2025)."},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3405451"},{"key":"e_1_2_11_25_1","doi-asserted-by":"crossref","unstructured":"Y.Tian J.Che Z.Zhang andZ.Yang \u201cFederated Learning With Unsourced Random Access \u201d in2023 IEEE 97th Vehicular Technology Conference (VTC2023\u2010Spring)(IEEE 2023) 1\u20135.","DOI":"10.1109\/VTC2023-Spring57618.2023.10201005"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3317300"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2000252"},{"key":"e_1_2_11_28_1","unstructured":"C.Wu Y.Ren D. K.So andJ.Tang \u201cAdaptive Biased User Scheduling for Heterogeneous Wireless Federate Learning Network \u201dpreprint arXiv:2505.05231(May 8 2025)."},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0309695"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3371169"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJCAS.2023.3299052"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3427013"},{"key":"e_1_2_11_33_1","unstructured":"L.Lv H.Jiang Z.Ding Q.Ye N.Al\u2010Dhahir andJ.Chen \u201cIntelligent Interference Engineering for Secure Non\u2010Orthogonal Multiple Access \u201dpreprint arXiv:2003.13488(March 30 2020)."},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3296319"},{"key":"e_1_2_11_35_1","first-page":"119","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Blanchard P.","year":"2017"},{"key":"e_1_2_11_36_1","unstructured":"D.Yin Y.Chen R.Kannan andP.Bartlett \u201cByzantine\u2010Robust Distributed Learning: Towards Optimal Statistical Rates \u201d inInternational Conference on Machine Learning(PMLR 2018) 5650\u20135659."},{"key":"e_1_2_11_37_1","doi-asserted-by":"crossref","unstructured":"X.Cao M.Fang J.Liu andN. Z.Gong \u201cFLTrust: Byzantine\u2010Robust Federated Learning via Trust Bootstrapping \u201dpreprint arXiv:2012.13995(December 27 2020).","DOI":"10.14722\/ndss.2021.24434"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2025.3551264"},{"key":"e_1_2_11_39_1","doi-asserted-by":"crossref","unstructured":"U.ShahulandJ.Harshan \u201cForta: Byzantine\u2010Resilient FL Aggregation via DFT\u2010Guided Krum \u201dpreprint arXiv:2507.14588(July 19 2025).","DOI":"10.1109\/ITW62417.2025.11240545"},{"key":"e_1_2_11_40_1","doi-asserted-by":"crossref","unstructured":"H. J.Huang H. T.Otal andM. A.Canbaz \u201cFederated Learning in Adversarial Environments: Testbed Design and Poisoning Resilience in Cybersecurity \u201dpreprint arXiv:2409.09794(September 15 2024).","DOI":"10.1109\/ICCWorkshops67674.2025.11162297"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3348409"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3201117"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3195067"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3447833"},{"key":"e_1_2_11_45_1","unstructured":"N. D.Pham T.Dayaratne V.Vo et\u00a0al. \u201cSelf\u2010Adaptive and Robust Federated Spectrum Sensing Without Benign Majority for Cellular Networks \u201dpreprint arXiv:2507.12127(July 16 2025)."},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3036747"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2844952"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3117256"},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.673"},{"key":"e_1_2_11_50_1","doi-asserted-by":"crossref","unstructured":"O.CelilandM.Dener \u201cDetecting IoT Botnet Attacks Using Machine Learning Methods \u201d in2020 International Conference on Information Security and Cryptology (ISCTURKEY)(IEEE 2020) 31\u201337.","DOI":"10.1109\/ISCTURKEY51113.2020.9307994"},{"issue":"1","key":"e_1_2_11_51_1","first-page":"388","article-title":"Grant\u2010Free NOMA for Massive Machine\u2010Type Communications: A Survey","volume":"25","author":"Celik A.","year":"2023","journal-title":"IEEE Communications Surveys & Tutorials"}],"container-title":["IET Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70138","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cmu2.70138","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T08:21:06Z","timestamp":1773130866000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cmu2.70138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/cmu2.70138"],"URL":"https:\/\/doi.org\/10.1049\/cmu2.70138","archive":["Portico"],"relation":{},"ISSN":["1751-8628","1751-8636"],"issn-type":[{"value":"1751-8628","type":"print"},{"value":"1751-8636","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-10-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70138"}}