{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T10:01:14Z","timestamp":1790071274782,"version":"4.0.1"},"reference-count":21,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Shanxi Provincial Key Laboratory of Data Element Innovation and Economic Decision Analysis","award":["2025-KF-02"],"award-info":[{"award-number":["2025-KF-02"]}]},{"name":"Shaanxi Provincial Social Science Foundation","award":["2024J280"],"award-info":[{"award-number":["2024J280"]}]},{"DOI":"10.13039\/501100009103","name":"Shaanxi Provincial Department of Education","doi-asserted-by":"publisher","award":["2030100790"],"award-info":[{"award-number":["2030100790"]}],"id":[{"id":"10.13039\/501100009103","id-type":"DOI","asserted-by":"publisher"}]},{"award":["2030100790"],"award-info":[{"award-number":["2030100790"]}],"id":[{"id":"https:\/\/ror.org\/00jb7xy46","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015974","name":"2024 State Grid Henan Cooperation","doi-asserted-by":"publisher","award":["5217L0240004"],"award-info":[{"award-number":["5217L0240004"]}],"id":[{"id":"10.13039\/501100015974","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Federated intrusion detection systems (FL-IDSs) for IoT and wireless sensor networks (WSNs) must remove client contributions after training when consent changes, devices retire, or compromised nodes are identified. Existing federated unlearning methods are not well aligned with transformer-based IDSs because they use coarse attribution, provide limited trajectory verification, and handle concurrent deletion requests weakly under rare-attack imbalance conditions. This paper proposes ARFU-IDS, a robust federated unlearning framework for transformer-based IoT and sensor-network IDSs. ARFU-IDS combines attention-head attribution, dual-path layer criticality probing, manipulation-resistant iterative verification, and conflict-graph scheduling to remove target-client influence while preserving retained detection utility. Experiments on UNSW-NB15, CICIoT2023, and IoTID20 evaluated detection utility, rare-category recall, adversarial robustness with network-flow feature triggers, and concurrent unlearning. On UNSW-NB15, ARFU-IDS achieves 87.1% Macro-F1 and 77.6% rare-category recall, within 0.2 percentage points of full retraining. Under flow-feature trigger attacks, it reduces attack success rate to 8.2% at f=0.1 and 9.7% at f=0.2. For three concurrent deletion requests, it shortens online unlearning latency by 43.3% relative to sequential processing. These results show that ARFU-IDS offers a practical route to robust and efficient federated unlearning for transformer-based IDSs in IoT and sensor-network deployments.<\/jats:p>","DOI":"10.3390\/s26185911","type":"journal-article","created":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T09:04:17Z","timestamp":1790067857000},"page":"5911","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ARFU-IDS: Robust Federated Unlearning for Transformer-Based Intrusion Detection in IoT and Sensor Networks"],"prefix":"10.3390","volume":"26","author":[{"given":"Xudong","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an 710048, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]},{"given":"Zhenyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an 710048, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"given":"Qiuyan","family":"Li","sequence":"additional","affiliation":[{"name":"State Grid Henan Electric Power Company Economic and Technological Research Institute, Zhengzhou 450052, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"given":"Zhenzhou","family":"Jing","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an 710048, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"}]},{"given":"Xuyao","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an 710048, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"}]},{"given":"Yuxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an 710048, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"visualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]},{"given":"Junwen","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Xi\u2019an Polytechnic University, Xi\u2019an 710048, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1007\/s10586-025-05325-w","article-title":"Federated Learning in Intrusion Detection: Advancements, Applications, and Future Directions","volume":"28","author":"Buyuktanir","year":"2025","journal-title":"Clust. Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"111023","DOI":"10.1016\/j.comnet.2024.111023","article-title":"A Review of Federated Learning Applications in Intrusion Detection Systems","volume":"258","author":"Belenguer","year":"2025","journal-title":"Comput. Netw."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Pecherle, G.D., Gy\u0151r\u0151di, R.\u015e., and Gy\u0151r\u0151di, C.A. (2026). Federated Learning-Based Intrusion Detection in Industrial IoT Networks. Future Internet, 18.","DOI":"10.3390\/fi18010002"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"8432654","DOI":"10.1049\/ise2\/8432654","article-title":"Enhancing IoT Security via Federated Learning: A Comprehensive Approach to Intrusion Detection","volume":"2025","author":"Bai","year":"2025","journal-title":"IET Inf. Secur."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, Y., and Guo, Y. (2025). Enhancing Intrusion Detection for IoT and Sensor Networks Through Semantic Analysis and Self-Supervised Embeddings. Sensors, 25.","DOI":"10.20944\/preprints202510.0523.v1"},{"key":"ref_6","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017). Communication-Efficient Learning of Deep Networks from Decentralized Data. Proceedings of the Artificial Intelligence Statistics (AISTATS), PMLR."},{"key":"ref_7","first-page":"11205","article-title":"Adapt-LFA: Adaptive Gradient-Guided Label Flipping Attack Against Federated Learning-Based Intrusion Detection in IoT","volume":"11","author":"Jebreel","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_8","first-page":"58237","article-title":"Defense Strategies in Federated Learning Against Adversarial Attacks: A Comprehensive Survey","volume":"12","author":"Shahid","year":"2024","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"11697","DOI":"10.1109\/TNNLS.2024.3478334","article-title":"Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics","volume":"36","author":"Romandini","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_10","unstructured":"Halimi, A., Kadhe, S., Rawat, A., and Baracaldo, N. (2022, January 23). Federated Unlearning: How to Efficiently Erase a Client in FL?. Proceedings of the ICML 2022 Workshop on Updatable Machine Learning (UpML), Baltimore, MD, USA."},{"key":"ref_11","first-page":"55","article-title":"Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience","volume":"Volume 14945","author":"Huynh","year":"2024","journal-title":"Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2024)"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhong, Z., Bao, W., Wang, J., Zhang, S., Zhou, J., Lyu, L., and Lim, W.Y.B. (2025). Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter. Proceedings of the IEEE CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52734.2025.02855"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Abd Elaziz, M., Fares, I.A., Dahou, A., and Shrahili, M. (2025). Federated Learning Framework for IoT Intrusion Detection Using Tab Transformer and Nature-Inspired Hyperparameter Optimization. Front. Big Data, 8.","DOI":"10.3389\/fdata.2025.1526480"},{"key":"ref_14","first-page":"103762","article-title":"DeepTransIDS: Transformer-Based Deep Learning Model for Detecting DDoS Attacks on 5G NIDD","volume":"25","author":"Kumar","year":"2025","journal-title":"Results Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., and Wolf, L. (2021). Transformer Interpretability Beyond Attention Visualization. Proceedings of the IEEE\/CVF Conference Computer Vision Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/978-981-96-8173-0_11","article-title":"FedSweep: Unlearning Backdoors in Federated Learning","volume":"Volume 15871","author":"Qiu","year":"2025","journal-title":"Proceedings of the Pacific-Asia Conference Knowledge Discovery Data Mining (PAKDD)"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Wang, W., Ma, Q., Zhang, Z., Liu, Y., Liu, Z., and Fang, M. (2025). Poisoning Attacks and Defenses to Federated Unlearning. Companion Proceedings of the ACM on Web Conference 2025 (WWW Companion), ACM.","DOI":"10.1145\/3701716.3715494"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1109\/TBDATA.2024.3409947","article-title":"Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation","volume":"11","author":"Xu","year":"2025","journal-title":"IEEE Trans. Big Data"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Moustafa, N., and Slay, J. (2015). UNSW-NB15: A Comprehensive Data Set for Network Intrusion Detection Systems. Proceedings of the Military Communications and Information Systems Conference (MilCIS), IEEE.","DOI":"10.1109\/MilCIS.2015.7348942"},{"key":"ref_20","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_21","doi-asserted-by":"crossref","unstructured":"Ullah, I., and Mahmoud, Q.H. (2020). A Scheme for Generating a Dataset for Anomalous Activity Detection in IoT Networks. Proceedings of the Canadian Conference on Artificial Intelligence, Springer.","DOI":"10.1007\/978-3-030-47358-7_52"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5911\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T09:12:01Z","timestamp":1790068321000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/18\/5911"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":21,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["s26185911"],"URL":"https:\/\/doi.org\/10.3390\/s26185911","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]}}}