{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T03:00:52Z","timestamp":1773716452400,"version":"3.50.1"},"reference-count":33,"publisher":"ASME International","issue":"7","license":[{"start":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T00:00:00Z","timestamp":1707091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.asme.org\/publications-submissions\/publishing-information\/legal-policies"}],"content-domain":{"domain":["asmedigitalcollection.asme.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The rapid advance in sensing technology has expedited data-driven innovation in manufacturing by enabling the collection of large amounts of data from factories. Big data provides an unprecedented opportunity for smart decision-making in the manufacturing process. However, big data also attracts cyberattacks and makes manufacturing systems vulnerable due to the inherent value of sensitive information. The increasing integration of artificial intelligence (AI) within smart factories also exposes manufacturing equipment susceptible to cyber threats, posing a critical risk to the integrity of smart manufacturing systems. Cyberattacks targeting manufacturing data can result in considerable financial losses and severe business disruption. Therefore, there is an urgent need to develop AI models that incorporate privacy-preserving methods to protect sensitive information implicit in the models against model inversion attacks. Hence, this paper presents the development of a new approach called mosaic neuron perturbation (MNP) to preserve latent information in the framework of the AI model, ensuring differential privacy requirements while mitigating the risk of model inversion attacks. MNP is flexible to implement into AI models, balancing the trade-off between model performance and robustness against cyberattacks while being highly scalable for large-scale computing. Experimental results, based on real-world manufacturing data collected from the computer numerical control (CNC) turning process, demonstrate that the proposed method significantly improves the ability to prevent inversion attacks while maintaining high prediction performance. The MNP method shows strong potential for making manufacturing systems both smart and secure by addressing the risk of data breaches while preserving the quality of AI models.<\/jats:p>","DOI":"10.1115\/1.4063728","type":"journal-article","created":{"date-parts":[[2023,10,10]],"date-time":"2023-10-10T07:14:20Z","timestamp":1696922060000},"update-policy":"https:\/\/doi.org\/10.1115\/crossmarkpolicy-asme","source":"Crossref","is-referenced-by-count":10,"title":["Privacy-Preserving Neural Networks for Smart Manufacturing"],"prefix":"10.1115","volume":"24","author":[{"given":"Hankang","family":"Lee","sequence":"first","affiliation":[{"name":"The Pennsylvania State University Industrial and Manufacturing Engineering, , University Park, PA 16802"}]},{"given":"Daniel","family":"Finke","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University The Applied Research Laboratory, , University Park, PA 16802"}]},{"given":"Hui","family":"Yang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University Industrial and Manufacturing Engineering, , University Park, PA 16802"}]}],"member":"33","published-online":{"date-parts":[[2024,2,5]]},"reference":[{"issue":"11","key":"2024020518382592200_CIT0001","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1080\/24725854.2018.1555383","article-title":"The Internet of Things for Smart Manufacturing: A Review","volume":"51","author":"Yang","year":"2019","journal-title":"IISE Trans."},{"key":"2024020518382592200_CIT0002","article-title":"X-Force Threat Intelligence Index 2022","author":"IBM","year":"2022"},{"key":"2024020518382592200_CIT0003","article-title":"2019 Global State of Cybersecurity in Small and Medium-Sized Businesses","author":"Ponemon-Institute","year":"2019"},{"key":"2024020518382592200_CIT0004","article-title":"A Survey of Privacy Attacks in Machine Learning","author":"Rigaki","year":"2020","journal-title":"ACM Comput. Surv."},{"key":"2024020518382592200_CIT0005","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.jmsy.2018.04.007","article-title":"Security of Smart Manufacturing Systems","volume":"47","author":"Tuptuk","year":"2018","journal-title":"J. Manuf. Syst."},{"key":"2024020518382592200_CIT0006","first-page":"111","article-title":"Robust De-anonymization of Large Sparse Datasets","author":"Narayanan","year":"2008"},{"issue":"3\u20134","key":"2024020518382592200_CIT0007","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The Algorithmic Foundations of Differential Privacy","volume":"9","author":"Dwork","year":"2014","journal-title":"Found. Trends Theor. Comput. Sci."},{"key":"2024020518382592200_CIT0008","first-page":"17","article-title":"Privacy in Pharmacogenetics: An End-to-End Case Study of Personalized Warfarin Dosing","author":"Fredrikson","year":"2014"},{"issue":"9","key":"2024020518382592200_CIT0009","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/JPROC.2023.3306773","article-title":"Trusted AI in Multiagent Systems: An Overview of Privacy and Security for Distributed Learning","volume":"111","author":"Ma","year":"2023","journal-title":"Proc. IEEE"},{"issue":"4","key":"2024020518382592200_CIT0010","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MCC.2016.79","article-title":"Cloud Manufacturing: Security, Privacy, and Forensic Concerns","volume":"3","author":"Esposito","year":"2016","journal-title":"IEEE Cloud Comput."},{"key":"2024020518382592200_CIT0011","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.jmsy.2018.03.006","article-title":"Cybersecurity for Digital Manufacturing","volume":"48","author":"Wu","year":"2018","journal-title":"J. Manuf. Syst."},{"issue":"5","key":"2024020518382592200_CIT0012","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1142\/S0218488502001648","article-title":"k-Anonymity: A Model for Protecting Privacy","volume":"10","author":"Sweeney","year":"2002","journal-title":"Int. J. Uncertainty Fuzziness Knowledge-Based Syst."},{"issue":"1","key":"2024020518382592200_CIT0013","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1109\/COMST.2019.2944748","article-title":"Differential Privacy Techniques for Cyber Physical Systems: A Survey","volume":"22","author":"Hassan","year":"2019","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"2024020518382592200_CIT0014","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1307.1370","article-title":"Matching Known Patients to Health Records in Washington State Data","author":"Sweeney","year":"2013","journal-title":"preprint arXiv:1307.1370"},{"key":"2024020518382592200_CIT0015","first-page":"265","article-title":"Calibrating Noise to Sensitivity in Private Data Analysis","author":"Dwork","year":"2006"},{"key":"2024020518382592200_CIT0016","first-page":"1322","article-title":"Model Inversion Attacks That Exploit Confidence Information and Basic Countermeasures","author":"Fredrikson","year":"2015"},{"issue":"29","key":"2024020518382592200_CIT0017","first-page":"1069","article-title":"Differentially Private Empirical Risk Minimization","volume":"12","author":"Chaudhuri","year":"2011","journal-title":"J. Mach. Learn. Res."},{"issue":"11","key":"2024020518382592200_CIT0018","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.14778\/2350229.2350253","article-title":"Functional Mechanism: Regression Analysis Under Differential Privacy","volume":"5","author":"Zhang","year":"2012","journal-title":"Proc. VLDB Endowment"},{"key":"2024020518382592200_CIT0019","first-page":"245","article-title":"Stochastic Gradient Descent With Differentially Private Updates","author":"Song","year":"2013"},{"key":"2024020518382592200_CIT0020","first-page":"1003","article-title":"Regression Model Fitting Under Differential Privacy and Model Inversion Attack","author":"Wang","year":"2015"},{"key":"2024020518382592200_CIT0021","first-page":"5714","article-title":"Gradient Mechanism to Preserve Differential Privacy and Deter Against Model Inversion Attacks in Healthcare Analytics","author":"Krall","year":"2020"},{"issue":"6","key":"2024020518382592200_CIT0022","doi-asserted-by":"publisher","first-page":"2184","DOI":"10.1109\/JBHI.2020.3036422","article-title":"Mosaic Privacy-Preserving Mechanisms for Healthcare Analytics","volume":"25","author":"Krall","year":"2020","journal-title":"IEEE J. Biomed. Health Inf."},{"issue":"2","key":"2024020518382592200_CIT0023","doi-asserted-by":"crossref","DOI":"10.1520\/SSMS20190043","article-title":"Privacy-Preserving Data Mining for Smart Manufacturing","volume":"4","author":"Hu","year":"2020","journal-title":"Smart Sustain. Manuf. Syst."},{"key":"2024020518382592200_CIT0024","first-page":"308","article-title":"Deep Learning With Differential Privacy","author":"Abadi","year":"2016"},{"issue":"7","key":"2024020518382592200_CIT0025","doi-asserted-by":"crossref","first-page":"5827","DOI":"10.1109\/JIOT.2019.2952146","article-title":"Local Differential Privacy for Deep Learning","volume":"7","author":"Arachchige","year":"2019","journal-title":"IEEE Internet Things J."},{"issue":"1","key":"2024020518382592200_CIT0026","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1109\/TCSS.2019.2950017","article-title":"DNN-DP: Differential Privacy Enabled Deep Neural Network Learning Framework for Sensitive Crowdsourcing Data","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Trans. Comput. Social Syst."},{"key":"2024020518382592200_CIT0027","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2002.08570","article-title":"Input Perturbation: A New Paradigm Between Central and Local Differential Privacy","author":"Kang","year":"2020","journal-title":"preprint arXiv:2002.08570"},{"key":"2024020518382592200_CIT0028","first-page":"8227","article-title":"Accuracy, Interpretability, and Differential Privacy Via Explainable Boosting","author":"Nori","year":"2021"},{"issue":"2","key":"2024020518382592200_CIT0029","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1109\/TDSC.2022.3144690","article-title":"Protecting Regression Models With Personalized Local Differential Privacy","volume":"20","author":"Li","year":"2022","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"2024020518382592200_CIT0030","first-page":"41","article-title":"Dp-util: Comprehensive Utility Analysis of Differential Privacy in Machine Learning","author":"Jarin","year":"2022"},{"key":"2024020518382592200_CIT0031","first-page":"148","article-title":"Model Inversion Attacks Against Collaborative Inference","author":"He","year":"2019"},{"issue":"1","key":"2024020518382592200_CIT0032","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks From Overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Machine Learning Res."},{"key":"2024020518382592200_CIT0033","doi-asserted-by":"publisher","first-page":"18326","DOI":"10.1109\/ACCESS.2020.2968172","article-title":"Sensor-Based Recurrence Analysis of Energy Efficiency in Machining Processes","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"}],"container-title":["Journal of Computing and Information Science in Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/7\/071002\/7238094\/jcise_24_7_071002.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article-pdf\/24\/7\/071002\/7238094\/jcise_24_7_071002.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:38:40Z","timestamp":1707158320000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmedigitalcollection.asme.org\/computingengineering\/article\/24\/7\/071002\/1169237\/Privacy-Preserving-Neural-Networks-for-Smart"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,5]]},"references-count":33,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7,1]]}},"URL":"https:\/\/doi.org\/10.1115\/1.4063728","relation":{},"ISSN":["1530-9827","1944-7078"],"issn-type":[{"value":"1530-9827","type":"print"},{"value":"1944-7078","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,5]]},"article-number":"071002"}}