{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:57:11Z","timestamp":1778345831151,"version":"3.51.4"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T00:00:00Z","timestamp":1716249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006469","name":"Fundo para o Desenvolvimento das Ci\u00eancias e da Tecnologia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006469","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Machine unlearning, which is crucial for data privacy and regulatory compliance, involves the selective removal of specific information from a machine learning model. This study focuses on implementing machine unlearning in Spiking Neuron Models (SNMs) that closely mimic biological neural network behaviors, aiming to enhance both flexibility and ethical compliance of AI models. We introduce a novel hybrid approach for machine unlearning in SNMs, which combines selective synaptic retraining, synaptic pruning, and adaptive neuron thresholding. This methodology is designed to effectively eliminate targeted information while preserving the overall integrity and performance of the neural network. Extensive experiments were conducted on various computer vision datasets to assess the impact of machine unlearning on critical performance metrics such as accuracy, precision, recall, and ROC AUC. Our findings indicate that the hybrid approach not only maintains but in some cases enhances the neural network's performance post-unlearning. The results confirm the practicality and efficiency of our approach, underscoring its applicability in real-world AI systems.<\/jats:p>","DOI":"10.3389\/fnbot.2024.1361577","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T05:00:42Z","timestamp":1716267642000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Machine unlearning in brain-inspired neural network paradigms"],"prefix":"10.3389","volume":"18","author":[{"given":"Chaoyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zuobin","family":"Ying","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijie","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,5,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4693","DOI":"10.1007\/s11063-021-10562-2","article-title":"A survey of encoding techniques for signal processing in spiking neural networks","volume":"53","author":"Auge","year":"2021","journal-title":"Neural Process. Lett"},{"key":"B2","article-title":"Online spatio-temporal learning in deep neural networks","author":"Bohnstingl","year":"2020","journal-title":"CoRR, abs\/2007.12723"},{"key":"B3","first-page":"141","article-title":"\u201cMachine unlearning,\u201d","volume-title":"42nd IEEE Symposium on Security and Privacy, SP 2021, San Francisco, CA, USA","author":"Bourtoule","year":"2021"},{"key":"B4","first-page":"735","article-title":"\u201cEfficient repair of polluted machine learning systems via causal unlearning,\u201d","volume-title":"Proceedings of the 2018 on Asia Conference on Computer and Communications Security, AsiaCCS 2018, Incheon, Republic of Korea","author":"Cao","year":"2018"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611838","article-title":"\u201cResource constrained model compression via minimax optimization for spiking neural networks,\u201d","author":"Chen","year":"2023","journal-title":"Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada"},{"key":"B6","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1145\/3460120.3484756","article-title":"\u201cWhen machine unlearning jeopardizes privacy,\u201d","volume-title":"CCS '21: 2021 ACM SIGSAC Conference on Computer and Communications Security, Virtual Event, Republic of Korea","author":"Chen","year":"2021"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2345","DOI":"10.1109\/TIFS.2023.3265506","article-title":"Zero-shot machine unlearning","volume":"18","author":"Chundawat","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur"},{"key":"B8","first-page":"21056","article-title":"\u201cDeep residual learning in spiking neural networks,\u201d","author":"Fang","year":"2021","journal-title":"Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021"},{"key":"B9","first-page":"3513","article-title":"\u201cMaking AI forget you: data deletion in machine learning,\u201d","volume-title":"Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","author":"Ginart","year":"2019"},{"key":"B10","first-page":"9301","article-title":"\u201cEternal sunshine of the spotless net: Selective forgetting in deep networks,\u201d","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA","author":"Golatkar","year":"2020"},{"key":"B11","article-title":"Training data protection with compositional diffusion models","author":"Golatkar","year":"2023","journal-title":"CoRR, abs\/2308.01937"},{"key":"B12","first-page":"11516","article-title":"\u201cAmnesiac machine learning,\u201d","volume-title":"Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event","author":"Graves","year":"2021"},{"key":"B13","doi-asserted-by":"publisher","first-page":"6406","DOI":"10.1109\/TCYB.2021.3069783","article-title":"Identification of fuzzy rule-based models with collaborative fuzzy clustering","volume":"52","author":"Hu","year":"2022","journal-title":"IEEE Trans. Cybern"},{"key":"B14","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/nn1218","article-title":"Neural activity and the dynamics of central nervous system development","volume":"7","author":"Hua","year":"2004","journal-title":"Nat. Neurosci"},{"key":"B15","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-031-21441-7_11","article-title":"\u201cCompetitive learning with spiking nets and spike timing dependent plasticity,\u201d","author":"Huyck","year":"2022","journal-title":"Artificial Intelligence XXXIX"},{"key":"B16","doi-asserted-by":"publisher","first-page":"4206","DOI":"10.1109\/TNNLS.2019.2952768","article-title":"A model for R(t) elements and R(t)-based spike-timing-dependent plasticity with basic circuit examples","volume":"31","author":"Ivans","year":"2020","journal-title":"IEEE Trans. Neural Networks Learn. Syst"},{"key":"B17","first-page":"107","article-title":"\u201cA survey on spiking neural networks in image processing,\u201d","volume-title":"Advances in Intelligent Systems and Computing","author":"Jose","year":"2014"},{"key":"B18","article-title":"Spiking neural networks and bio-inspired supervised deep learning: a survey","author":"Lagani","year":"2023","journal-title":"CoRR, abs\/2307.16235"},{"key":"B19","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1145\/3510854","article-title":"Saarsp: An architecture for systolic-array acceleration of recurrent spiking neural networks","volume":"18","author":"Lee","year":"2022","journal-title":"ACM J. Emerg. Technol. Comput. Syst"},{"key":"B20","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1145\/3520133","article-title":"Synaptic activity and hardware footprint of spiking neural networks in digital neuromorphic systems","volume":"21","author":"Lemaire","year":"2022","journal-title":"ACM Trans. Embed. Comput. Syst"},{"key":"B21","unstructured":"\u201cLearnable surrogate gradient for direct training spiking neural networks,\u201d30023010\n            LianS.\n            ShenJ.\n            LiuQ.\n            WangZ.\n            YanR.\n            TangH.\n          10.24963\/ijcai.2023\/335Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 20232023"},{"key":"B22","doi-asserted-by":"publisher","first-page":"39600","DOI":"10.32604\/iasc.2023.039600","article-title":"Attentive neighborhood feature augmentation for semi-supervised learning","volume":"37","author":"Liu","year":"2023","journal-title":"Intell. Autom. Soft Comput"},{"key":"B23","unstructured":"\u201cSpiking convolutional neural networks for text classification,\u201d\n            LvC.\n            XuJ.\n            ZhengX.\n          37710902The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda2023"},{"key":"B24","doi-asserted-by":"publisher","first-page":"3194","DOI":"10.1109\/TDSC.2022.3194884","article-title":"Learn to forget: machine unlearning via neuron masking","volume":"20","author":"Ma","year":"2023","journal-title":"IEEE Trans. Dependable Secur. Comput"},{"key":"B25","unstructured":"\u201cMachine unlearning of federated clusters,\u201d\n            PanC.\n            SimaJ.\n            PrakashS.\n            RanaV.\n            MilenkovicO.\n          The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda2023"},{"key":"B26","doi-asserted-by":"publisher","first-page":"38241","DOI":"10.32604\/iasc.2023.038241","article-title":"Instance reweighting adversarial training based on confused label","volume":"37","author":"Qiu","year":"2023","journal-title":"Intell. Autom. Soft Comput"},{"key":"B27","article-title":"Learn to unlearn: A survey on machine unlearning","author":"Qu","year":"2023","journal-title":"CoRR, abs\/2305.07512"},{"key":"B28","article-title":"Machine unlearning via algorithmic stability","author":"Ullah","year":"2021","journal-title":"CoRR, abs\/2102.13179"},{"key":"B29","doi-asserted-by":"publisher","first-page":"126832","DOI":"10.1016\/j.neucom.2023.126832","article-title":"BP-SRM: A directly training algorithm for spiking neural network constructed by spike response model","volume":"560","author":"Wang","year":"2023","journal-title":"Neurocomputing"},{"key":"B30","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s12293-022-00373-w","article-title":"A hierarchical taxonomic survey of spiking neural networks","volume":"14","author":"Wang","year":"2022","journal-title":"Memetic Comput"},{"key":"B31","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.ins.2019.07.023","article-title":"Multilevel similarity model for high-resolution remote sensing image registration","volume":"505","author":"Wang","year":"2019","journal-title":"Inf. Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1145\/3603620","article-title":"Machine unlearning: a survey","volume":"56","author":"Xu","year":"2024","journal-title":"ACM Comput. Surv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"11600","DOI":"10.1109\/TPAMI.2023.3286121","article-title":"CQ++ training: Minimizing accuracy loss in conversion from convolutional neural networks to spiking neural networks","volume":"45","author":"Yan","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B34","doi-asserted-by":"publisher","first-page":"4732","DOI":"10.1109\/TIFS.2023.3297905","article-title":"Fedrecovery: Differentially private machine unlearning for federated learning frameworks","volume":"18","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur"},{"key":"B35","first-page":"514","article-title":"\u201cDynamically selected mixup machine unlearning,\u201d","volume-title":"IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2022, Wuhan, China","author":"Zhou","year":"2022"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1361577\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T05:00:53Z","timestamp":1716267653000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1361577\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,21]]},"references-count":35,"alternative-id":["10.3389\/fnbot.2024.1361577"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1361577","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,21]]},"article-number":"1361577"}}