{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T07:45:38Z","timestamp":1763451938463,"version":"3.45.0"},"reference-count":48,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:00:00Z","timestamp":1760572800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Security and Privacy"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>This study introduces a BERT\u2010LSTM\u2010GRU hybrid model for dynamic Risk\u2010Adaptive Access Control (RAdAC), designed to enhance predictive accuracy, robustness, and scalability in real\u2010time IoT and cloud environments. The proposed model integrates BERT's contextual embeddings with LSTM and GRU's sequential modeling capabilities, unified by a novel Dynamic Risk\u2010Aware Contextual Fusion Module (DRCFM) that employs risk\u2010aware attention and reinforcement learning to dynamically adapt to varying risk levels. Adversarial training and explainable AI techniques further bolster the model's resilience and transparency. Evaluated on five diverse datasets, the model achieves 96% accuracy, 97% F1 score, and 0.99 AUC\u2010ROC on the Human Activity Recognition dataset, outperforming state\u2010of\u2010the\u2010art baselines by up to 5% in accuracy. Under adversarial attacks (FGSM, PGD), it retains 92% accuracy (FGSM) and 90% accuracy (PGD) on the same dataset, demonstrating a 14% robustness improvement over baselines. Scalability analysis reveals a minimal 3% accuracy drop when scaling from 10\u2009000 to 1\u2009000\u2009000 instances, with an inference time of 14\u2009ms per instance, supporting real\u2010time applications. An ablation study underscores the contributions of each component, with BERT improving accuracy by approximately 5%\u20136%, LSTM by 5%, and GRU by 4%. These results position the model as a comprehensive solution for dynamic access control, with future research directions including multi\u2010modal data integration, edge deployment, and advanced explainability techniques to further enhance its applicability and trustworthiness in secure systems.<\/jats:p>","DOI":"10.1002\/spy2.70114","type":"journal-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T01:53:47Z","timestamp":1760666027000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real\u2010Time Risk\u2010Adaptive Access Control With\n                    <scp>DRCFM<\/scp>\n                    : A Scalable\n                    <scp>BERT<\/scp>\n                    \u2010\n                    <scp>LSTM<\/scp>\n                    \u2010\n                    <scp>GRU<\/scp>\n                    Framework for Secure Systems"],"prefix":"10.1002","volume":"8","author":[{"given":"Donya","family":"Piriaei","sequence":"first","affiliation":[{"name":"Department of Computer Engineering Borujerd Branch, Islamic Azad University  Borujerd Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5820-9753","authenticated-orcid":false,"given":"Afshin","family":"Rezakhani","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Faculty of Engineering Ayatollah Boroujerdi University  Borujerd Iran"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0082-036X","authenticated-orcid":false,"given":"Hamid","family":"Haj Seyyed Javadi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering Shahed University  Tehran Iran"}]},{"given":"Leila","family":"Rikhtechi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering Borujerd Branch, Islamic Azad University  Borujerd Iran"}]}],"member":"311","published-online":{"date-parts":[[2025,10,16]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10586\u2010018\u20101850\u20107"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2947377"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2969326"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672200.3673880"},{"key":"e_1_2_9_6_1","unstructured":"A.Abusini \u201cEnhancing Smart Home Security Through Risk\u2010Based Access Control (RBAC): Closing the Gap \u201d2024Doctoral diss. Dakota State University."},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2024.055287"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.6633\/IJNS.202309_25(5).02"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/math12162541"},{"key":"e_1_2_9_10_1","first-page":"253","volume-title":"Algorithms for Intelligent Systems: Artificial Intelligence and Sustainable Computing (Proceedings of ICSISCET 2021)","author":"Athanere S.","year":"2022"},{"issue":"3","key":"e_1_2_9_11_1","first-page":"231","article-title":"A New Risk\u2010Based Decentralized Model for Peer\u2010To\u2010Peer Energy Trading Among Smart Homes. International Journal of Industrial Electronics","volume":"5","author":"Mohammadi N.","year":"2022","journal-title":"Control and Optimization"},{"key":"e_1_2_9_12_1","unstructured":"R.Houtsma \u201cAn Explainable Machine Learning Approach to Risk\u2010Adaptive Access Control \u201dMaster's thesis University of Twente University of Twente 2022."},{"key":"e_1_2_9_13_1","first-page":"1","volume-title":"Proceedings of the 2022 International Joint Conference on Neural Networks (IJCNN)","author":"Li Z.","year":"2022"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105022"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2022.106836"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmes.2023.030131"},{"issue":"7","key":"e_1_2_9_17_1","first-page":"43","article-title":"LSTM vs GRU for Time Series","volume":"12","author":"Kozlov S. V.","year":"2024","journal-title":"International Journal of Open Information Technologies"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/computers11020016"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201075648\u2010y"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2023.109626"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100898"},{"volume-title":"Proceedings of the 2024 IEEE 3rd International Conference on Computing and Machine Intelligence (ICCMI)","year":"2024","author":"Alboqmi R.","key":"e_1_2_9_22_1"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10207\u2010024\u201000977\u2010y"},{"key":"e_1_2_9_24_1","unstructured":"A.Fasanmade A. H.Al\u2010Bayatti J. N.Morden andF.Caraffini \u201cContext\u2010Aware Quantitative Risk Assessment Machine Learning Model for Drivers Distraction \u201d2024arXiv preprint arXiv:2402.13421."},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537\u2010023\u201000783\u20108"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2024.055167"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.54254\/2755\u20102721\/77\/2024MA0064"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2023.102257"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2024.1358184"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3210372"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooae110"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13053187"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.3390\/engproc2023039017"},{"issue":"6","key":"e_1_2_9_34_1","first-page":"133","article-title":"Software Complex for Risk\u2010Oriented Attribute\u2010Based Access Control Mechanism","volume":"12","author":"Shitov A.","year":"2024","journal-title":"International Journal of Open Information Technologies"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.025"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652\u2010020\u201002758\u20102"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.3390\/math12162541"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10207\u2010024\u201000866\u20104"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589608.3593841"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1186\/s42400\u2010024\u201000320\u2010x"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577923.3583648"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3256374"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"R.Liang J.Chen C.Wu et al. \u201cVulseye: Detect Smart Contract Vulnerabilities via Stateful Directed Graybox Fuzzing \u201d2024 arXiv preprint arXiv:2408.10116.","DOI":"10.1109\/TIFS.2025.3537827"},{"key":"e_1_2_9_44_1","doi-asserted-by":"crossref","unstructured":"R.Liang J.Chen C.Wu et al. \u201cPonziGuard: Towards Effective Detection of Ponzi Schemes on Ethereum With Contract Runtime Behavior Graph \u201d2024 arXiv preprint arXiv:2406.00921.","DOI":"10.1145\/3597503.3623318"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3623318"},{"key":"e_1_2_9_46_1","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin J.","year":"2019"},{"key":"e_1_2_9_47_1","unstructured":"J.Chung C.Gulcehre K.Cho andY.Bengio \u201cEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling \u201d2014arXiv preprint arXiv:1412.3555."},{"key":"e_1_2_9_48_1","unstructured":"Amazon.com \u201cAmazon Employee Lgoaccess Challenge \u201dKaggle 2024 https:\/\/www.kaggle.com\/datasets\/amazon."},{"key":"e_1_2_9_49_1","unstructured":"K.Montanez \u201cAmazon Access Samples \u201dUCI Machine Learning Repository: Amazon Access Samples Data Set 2024 https:\/\/archive.ics.uci.edu\/ml\/datasets."}],"container-title":["SECURITY AND PRIVACY"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/spy2.70114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T07:42:07Z","timestamp":1763451727000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/spy2.70114"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,16]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1002\/spy2.70114"],"URL":"https:\/\/doi.org\/10.1002\/spy2.70114","archive":["Portico"],"relation":{},"ISSN":["2475-6725","2475-6725"],"issn-type":[{"type":"print","value":"2475-6725"},{"type":"electronic","value":"2475-6725"}],"subject":[],"published":{"date-parts":[[2025,10,16]]},"assertion":[{"value":"2025-05-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70114"}}