{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:30:15Z","timestamp":1787725815348,"version":"build-2784847793"},"reference-count":60,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Stronger defense mechanisms are needed for the safety of healthcare IoT systems, for faster detection and smooth recovery from cyber-attacks, without disrupting services. This study addresses the need to safeguard healthcare IoT systems through efficient detection of potential anomalies leveraging the capacities of deep learning, and also rolling back the system to the safest checkpoint in the recent past, verified using post-quantum verification using ML-DSA\/CRYSTALS-Dilithium. A two-tier architecture is proposed in this study with deep anomaly detection and attack severity analysis in the first tier, and post-quantum verification for selecting a policy-driven safe rollback point based on multi-factor assessment, with due consideration of risks. The reinforcement learning-based framework is used in the checkpoint selection phase that selects the checkpoint with the best Q-Score. The model is implemented over two prominent HIoT network datasets\u2013WUSTL EHMS 2020 and CIC IoMT 2024. The model is evaluated using anomaly detection metrics (attack probability, confidence score, severity analysis, and recovery uptime), trust score, verification latency, recovery time, rollback quality, and performance metrics (F1-score, false-positive rate, precision, and recall). The proposed model achieved strong overall performance across both healthcare IoT datasets, with average values of 59.23% attack probability, 94.00% confidence, 5.61% anomaly score, 69.50% severity, 26.61 ns recovery time, 75.86% trust score, 98.37% uptime, 72.93% rollback quality, 11.28 ns verification latency, 98.37% F1-score, 98.28% recall, 98.4% precision, and 0.045% false positive rate. The proposed model effectively and accurately detects an attack and proposes the suitable recovery method\u2013micro rollback, medium rollback, or complete rollback- based on the attack severity analysis. Better system uptime is ensured by selecting recent and trustworthy checkpoints to roll back based on post-quantum verification and combined trust score calculation.<\/jats:p>","DOI":"10.3389\/frai.2026.1913803","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:04:30Z","timestamp":1787724270000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A post-quantum verified self-healing framework for healthcare IoT systems: deep anomaly detection, severity estimation and risk-aware rollback to trusted checkpoints"],"prefix":"10.3389","volume":"9","author":[{"given":"Arul Treesa","family":"Mathew","sequence":"first","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prasanna","family":"Mani","sequence":"additional","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore","place":["Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICADS69450.2026.11545502","article-title":"\u201cQuantum-resistant cryptography for secure IoT communication systems,\u201d","author":"Aakash","year":"2026","journal-title":"2026 International conference on air defense and security (ICADS)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"189","DOI":"10.3390\/computers15030189","article-title":"Post-quantum authentication in the internet of medical things: a system-level review and future directions","volume":"15","author":"Abdullah","year":"2026","journal-title":"Computers"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2607.02687","article-title":"RES-DARE: failure-aware expert adaptation and rollback-safe self-repair for intrusion detection","author":"Aftab","year":"2026","journal-title":"arXiv"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1813265","DOI":"10.3389\/fdata.2026.1813265","article-title":"Interpretable intrusion detection for IoT: a CNN-BiLSTM permutation importance framework for deep feature selection","volume":"9","author":"Al-Shibly","year":"2026","journal-title":"Front. Big Data"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.65500\/computics-2025-003","article-title":"Artificial intelligence-driven intrusion detection systems for secure healthcare IoT: a comprehensive review","volume":"1","author":"Baba","year":"2025","journal-title":"Impact Comput"},{"key":"B6","doi-asserted-by":"publisher","first-page":"116","DOI":"10.47514\/phyaccess.2025.5.1.013","article-title":"Post-quantum cryptographic frameworks for internet of things (IoT) and internet of medical things (IoMT) authentication systems","volume":"5","author":"Barna","year":"2025","journal-title":"Phys. Access"},{"key":"B7","doi-asserted-by":"publisher","first-page":"95","DOI":"10.53022\/oarjet.2025.8.1.0033","article-title":"Enhancing healthcare IoT (H-IoT) resilience: a comprehensive review","volume":"8","author":"Bisola","year":"2025","journal-title":"Open Access Res. J. Eng. Technol"},{"key":"B8","first-page":"927","article-title":"\u201cResilience in smart healthcare systems,\u201d","author":"B\u00f6k","year":"2025","journal-title":"Handbook on Smart Health"},{"key":"B9","doi-asserted-by":"crossref","unstructured":"Dadkhah\n              S.\n            \n            \n              Neto\n              E. C. P.\n            \n            \n              Ferreira\n              R.\n            \n            \n              Molokwu\n              R. C.\n            \n            \n              Sadeghi\n              S.\n            \n          \n          CICIoMT2024: A Benchmark Dataset for Multi-Protocol Security Assessment in IoMT. Canadian Institute for Cybersecurity, University of New Brunswick\n          \n          2024","DOI":"10.1016\/j.iot.2024.101351"},{"key":"B10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.5753\/sscad_estendido.2025.15828","article-title":"\u201cA performance analysis of system rollback techniques,\u201d","author":"de Souza","year":"2025","journal-title":"Simp\u00f3sio em Sistemas Computacionais de Alto Desempenho (SSCAD)"},{"key":"B11","author":"Dinu","year":"2025","journal-title":"Migration to Post-Quantum Cryptography: From ECDSA to ML-DSA"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.22762","article-title":"TRUSTCHECKPOINTS: time betrays malware for unconditional software root of trust","author":"Doku","year":"2025","journal-title":"arXiv"},{"key":"B13","doi-asserted-by":"publisher","first-page":"44624","DOI":"10.1038\/s41598-025-32697-1","article-title":"A novel deep learning framework with temporal attention convolutional networks for intrusion detection in IoT and IIoT networks","volume":"15","author":"Ghosh","year":"2025","journal-title":"Sci. Rep"},{"key":"B14","unstructured":"Hady\n              A. A.\n            \n            \n              Ghubaish\n              A.\n            \n            \n              Salman\n              T.\n            \n            \n              Unal\n              D.\n            \n            \n              Jain\n              R.\n            \n          \n          WUSTL-EHMS-2020 Dataset for Internet of Medical Things (IoMT) Security\n          \n          2020"},{"key":"B15","doi-asserted-by":"publisher","first-page":"101650","DOI":"10.1016\/j.iot.2025.101650","article-title":"A comprehensive and realistic performance evaluation of post-quantum security for consumer iot devices","volume":"33","author":"Hanna","year":"2025","journal-title":"Internet Things"},{"key":"B16","doi-asserted-by":"publisher","first-page":"207","DOI":"10.5220\/0013203700003944","article-title":"\u201cEnhanced intrusion detection in IIoT networks: a lightweight approach with autoencoder-based feature learning,\u201d","author":"Hasan","year":"2025","journal-title":"Proceedings of the 10th international conference on internet of things, big data and security (IoTBDS 2025)"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e0348600","DOI":"10.1371\/journal.pone.0348600","article-title":"Post-quantum cognitive zero trust architecture for healthcare iot devices","volume":"21","author":"Hussain","year":"2026","journal-title":"PLoS ONE"},{"key":"B18","doi-asserted-by":"publisher","first-page":"111","DOI":"10.46810\/tdfd.1883893","article-title":"Comparative performance analysis of classical and post-quantum cryptography (FIPS 203\/204) on ARMv8 IoT devices across NIST security levels","volume":"15","author":"\u0130nce","year":"2026","journal-title":"Turk. J. Nat. Sci"},{"key":"B19","doi-asserted-by":"publisher","first-page":"20413","DOI":"10.1109\/JIOT.2026.3668885","article-title":"\u201cEcoAIoT: a survey on ecological and sustainable aiot systems with energy harvesting,\u201d","author":"Jing","year":"2026","journal-title":"IEEE internet of things journal"},{"key":"B20","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1007\/978-3-032-12930-7_15","article-title":"\u201cA multi-layer perceptron approach for detecting network-layer attacks in IoT networks,\u201d","author":"Kadiyala","year":"2025","journal-title":"International conference on the AI revolution, Las Vegas, USA"},{"key":"B21","unstructured":"Khalil\n              M.\n            \n          \n          IoT hacking statistics 2025: Threats, Risks\n          \n          2025"},{"key":"B22","first-page":"48","article-title":"\u201cSecuring IoT in the post-quantum era: implementation, challenges and future directions,\u201d","volume-title":"IEEE communications standards magazine","author":"Khan","year":"2025"},{"key":"B23","doi-asserted-by":"publisher","first-page":"24604","DOI":"10.1109\/JIOT.2026.3673083","article-title":"\u201cPost-quantum secure lattice-based lightweight authentication and key agreement scheme for multi-layer IoT-enabled smart grid system,\u201d","author":"Kumar","year":"2026","journal-title":"IEEE internet of things journal"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IC366947.2025.11290214","article-title":"\u201cFederated learning for de-centralized self-healing in edge-iot networks,\u201d","author":"Kumar","year":"2025","journal-title":"2025 seventeenth international conference on contemporary computing (IC3)"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ISAS66241.2025.11101769","article-title":"\u201cClassification of network anomalies using a multilayer perceptron,\u201d","author":"Kushnerov","year":"2025","journal-title":"2025 9th international symposium on innovative approaches in smart technologies (ISAS)"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/s10270-026-01399-1","article-title":"Formal verification of fault tolerance mechanisms in multi-layer iot using event-b: M. ltaief et al","author":"Ltaief","year":"2026","journal-title":"Softw. Syst. Model"},{"key":"B27","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1186\/s42400-025-00465-3","article-title":"HIoT: heterogeneous information network based compromised IoT device detection","volume":"9","author":"Luo","year":"2026","journal-title":"Cybersecurity"},{"key":"B28","doi-asserted-by":"publisher","first-page":"7749","DOI":"10.1109\/JIOT.2025.3564722","article-title":"\u201cFederated learning and resource-aware graph neural network for intrusion detection in 6G-IoT driven healthcare system,\u201d","author":"Ma","year":"2026","journal-title":"IEEE internet of things journal, Vol. 13"},{"key":"B29","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s10586-024-04799-4","article-title":"Securing the future: exploring post-quantum cryptography for authentication and user privacy in IoT devices","volume":"28","author":"Mansoor","year":"2025","journal-title":"Cluster Comput"},{"key":"B30","doi-asserted-by":"publisher","first-page":"10465","DOI":"10.1109\/OJCOMS.2025.3644132","article-title":"\u201cIntegrating zero trust architecture in O-RAN: a comprehensive survey and analysis,\u201d","author":"Mehrban","year":"2025","journal-title":"IEEE open journal of the communications society Vol. 6"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.46298\/lmcs-21(1:2)2025","article-title":"Checkpoint-based rollback recovery in session programming","author":"Mezzina","year":"2025","journal-title":"Logic. Methods Comput. Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1109\/TNSM.2025.3647853","article-title":"\u201cA threshold-triggered deep Q-network-based framework for self-healing in autonomic software-defined IIoT-edge networks,\u201d","author":"Mwangi","year":"2025","journal-title":"IEEE transactions on network and service management"},{"key":"B33","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1007\/s10462-024-11101-w","article-title":"A comprehensive and systematic literature review on intrusion detection systems in the internet of medical things: current status, challenges, and opportunities","volume":"58","author":"Naghib","year":"2025","journal-title":"Artif. Intell. Rev"},{"key":"B34","doi-asserted-by":"publisher","first-page":"31039","DOI":"10.1038\/s41598-025-15292-2","article-title":"Hybrid deep learning-enabled framework for enhancing security, data integrity, and operational performance in healthcare internet of things (H-IoT) environments","volume":"15","author":"Naik","year":"2025","journal-title":"Sci. Rep"},{"key":"B35","doi-asserted-by":"publisher","first-page":"126854","DOI":"10.1016\/j.eswa.2025.126854","article-title":"Improved network anomaly detection system using optimized autoencoder \u2013 LSTM","volume":"273","author":"Narmadha","year":"2025","journal-title":"Expert Syst. Appl"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICITEICS64870.2025.11341204","article-title":"\u201cAutoPilot AI: architecting self-healing ml systems with reinforcement feedback loops,\u201d","author":"Nellutla","year":"2025","journal-title":"2025 IEEE 2nd international conference on information technology, electronics and intelligent communication systems (ICITEICS)"},{"key":"B37","doi-asserted-by":"publisher","first-page":"100572","DOI":"10.1016\/j.mlwa.2024.100572","article-title":"A comprehensive study of auto-encoders for anomaly detection: efficiency and trade-offs","volume":"17","author":"Neloy","year":"2024","journal-title":"Mach. Learn. Appl"},{"key":"B38","year":"2024","journal-title":"Module-Lattice-Based Digital Signature Standard"},{"key":"B39","doi-asserted-by":"publisher","first-page":"294","DOI":"10.22247\/ijcna\/2026\/16","article-title":"Enhanced anomaly detection in networks using auto-encoders with feature selection techniques and hybrid deep learning","volume":"13","author":"Oleiwi","year":"2026","journal-title":"Int. J. Comput. Netw. Appl"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1723966","DOI":"10.3389\/fphy.2025.1723966","article-title":"Design and implementation of an authenticated post-quantum session protocol using ML-KEM (Kyber), ML-DSA (Dilithium), and AES-256-GCM","volume":"13","author":"Olushola","year":"2026","journal-title":"Front. Phys"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2604.07360","article-title":"Position paper: from edge AI to adaptive edge AI","author":"Pittorino","year":"2026","journal-title":"arXiv"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/EDCT65302.2025.11495832","article-title":"\u201cHybrid random forest and LSTM detection with reinforcement learning recovery for self-healing IoT wireless networks,\u201d","author":"Ram Kumar","year":"2025","journal-title":"2025 2nd international conference on emerging trends in electronic devices and computational techniques (EDCT)"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ETFA65518.2025.11205628","article-title":"\u201cAutomatic recovery of run-time threats in distributed industrial control systems,\u201d","author":"Raptis","year":"2025","journal-title":"2025 IEEE 30th international conference on emerging technologies and factory automation (ETFA)"},{"key":"B44","doi-asserted-by":"publisher","first-page":"e3502","DOI":"10.7717\/peerj-cs.3502","article-title":"AI and post-quantum cryptography powered cybersecurity approaches for IoT systems: a literature review","volume":"12","author":"Saeed","year":"2026","journal-title":"PeerJ Comput. Sci"},{"key":"B45","doi-asserted-by":"publisher","first-page":"136","DOI":"10.14445\/22315381\/IJETT-V72I6P114","article-title":"Multilayer perceptron and auto-encoder based intrusion detection system","volume":"72","author":"Sahitya","year":"2024","journal-title":"Int. J. Eng. Trends Technol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"6867","DOI":"10.3390\/s25226867","article-title":"Lightweight ECC-based self-healing federated learning framework for secure IIoT networks","volume":"25","author":"Salim","year":"2025","journal-title":"Sensors"},{"key":"B47","doi-asserted-by":"publisher","first-page":"10246","DOI":"10.1038\/s41598-025-93473-9","article-title":"A multilayer deep autoencoder approach for cross layer IoT attack detection using deep learning algorithms","volume":"15","author":"Saranya","year":"2025","journal-title":"Sci. Rep"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICBMESH66209.2025.11182231","article-title":"\u201cIoMT enabled advanced cyber-attack detection model (iACDM) for secure healthcare system,\u201d","author":"Shanmuga Priya","year":"2025","journal-title":"2025 international conference on biomedical engineering and sustainable healthcare (ICBMESH)"},{"key":"B49","doi-asserted-by":"publisher","first-page":"4925","DOI":"10.1109\/TCE.2025.3569904","article-title":"\u201cPost-quantum cryptography (PQC) for IoT-consumer electronics devices integrated with deep learning,\u201d","author":"Sharma","year":"2025","journal-title":"IEEE transactions on consumer electronics"},{"key":"B50","doi-asserted-by":"publisher","first-page":"6261","DOI":"10.3390\/s25206261","article-title":"A comprehensive survey on intrusion detection systems for healthcare 5.0: concepts, challenges, and practical applications","volume":"25","author":"Siqueira","year":"2025","journal-title":"Sensors"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2025.3573097","article-title":"\u201cInterpretable and adaptive GAN-BiLSTM approach for cyber threat detection in IoMT-based healthcare 5.0,\u201d","author":"Ullah","year":"2025","journal-title":"IEEE journal of biomedical and health informatics"},{"key":"B52","doi-asserted-by":"publisher","first-page":"40865","DOI":"10.1038\/s41598-025-24459-w","article-title":"CyberDetect MLP a big data enabled optimized deep learning framework for scalable cyberattack detection in IoT environments","volume":"15","author":"Upender","year":"2025","journal-title":"Sci. Rep"},{"key":"B53","doi-asserted-by":"publisher","first-page":"44","DOI":"10.69996\/jsihs.2025014","article-title":"Quantum-secure iot networks for the 6G era: post-quantum cryptography, blockchain integration, and trust architectures-a comprehensive review","volume":"3","author":"Vaigandla","year":"2025","journal-title":"J. Sensors IoT Health Sci"},{"key":"B54","doi-asserted-by":"publisher","first-page":"173","DOI":"10.63278\/jicrcr.vi.3609","article-title":"Self-healing distributed networks for AI systems: a paradigm shift in resilient architecture","volume":"9","author":"Veeravalli","year":"2026","journal-title":"J. Int. Crisis Risk Commun. Res"},{"key":"B55","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1109\/UPWIECON67212.2025.11390538","article-title":"\u201cGenerative AI for IoT security: a review of attack detection, prevention, and secure data transmission mechanisms,\u201d","author":"Wankhade","year":"2025","journal-title":"2025 1st IEEE Uttar Pradesh section women in engineering international conference on electrical electronics and computer engineering (UPWIECON)"},{"key":"B56","doi-asserted-by":"publisher","first-page":"41994","DOI":"10.1109\/ACCESS.2025.3547572","article-title":"Anomaly-based intrusion detection for iomt networks: design, implementation, dataset generation, and ML algorithms evaluation","volume":"13","author":"Zachos","year":"2025","journal-title":"IEEE Access"},{"key":"B57","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/CITSC64390.2025.00174","article-title":"\u201cEnhancing survivability in power iot systems based on compliance checks,\u201d","author":"Zekun","year":"2025","journal-title":"2025 Asia-Europe conference on cybersecurity, internet of things and soft computing (CITSC)"},{"key":"B58","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1109\/TR.2025.3528256","article-title":"Evolutionary adversarial autoencoder for unsupervised anomaly detection of industrial internet of things","volume":"74","author":"Zeng","year":"2025","journal-title":"IEEE Trans. Reliab"},{"key":"B59","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/SCECS65243.2025.11065049","article-title":"\u201cEdge computing intrusion detection algorithm based on transformer and autoencoder,\u201d","author":"Zhang","year":"2025","journal-title":"2025 international conference on sensor-cloud and edge computing system (SCECS)"},{"key":"B60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICDSEC67721.2025.11439375","article-title":"\u201cAnomaly access detection method for edge devices using variational autoencoder algorithms,\u201d","author":"Zhang","year":"2025","journal-title":"2025 international conference on data science and edge computing (ICDSEC)"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1913803\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:04:32Z","timestamp":1787724272000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1913803\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":60,"alternative-id":["10.3389\/frai.2026.1913803"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1913803","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"article-number":"1913803"}}