{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T17:09:37Z","timestamp":1776791377495,"version":"3.51.2"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Things"],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:p>Modern vehicles increasingly rely on advanced driver monitoring systems (DMS) to ensure safety and enhance the driving experience. These systems assess driver status to prevent accidents caused by fatigue, inattentiveness, or intoxication. While some DMS applications process video data on vehicle, many rely on edge or cloud-based solutions, raising significant privacy concerns due to the storage of sensor data from vehicles. Existing approaches, such as de-identification and homomorphic encryption, either impose heavy computational overhead on vehicles or insufficiently address privacy.<\/jats:p>\n                  <jats:p>To overcome these limitations, we present the Privacy-preserving Driver Monitoring System (PDMS), a novel framework based on the additive secret sharing theory and privacy-preserving Transformer-based deep learning models. PDMS creates randomized secret shares from driver\u2019s facial video data on vehicle, processes them independently through privacy-preserving Transformer models on edges, and securely aggregates partial results on vehicle, ensuring vehicles\u2019 sensor data and final results remain protected. This approach reduces the computational load on the vehicle, enabling cost-effective and scalable DMS solutions that protect the privacy of the driver both in transit and in processing.<\/jats:p>\n                  <jats:p>Our contributions include the design and optimization of the PDMS system, incorporating privacy-preserving DNN layers that are capable of processing randomized secret shares. Furthermore, we present a practical system that utilizes a vision transformer (ViT)-based gaze estimation model, demonstrating the effectiveness of PDMS through comprehensive experiments.<\/jats:p>","DOI":"10.1145\/3777384","type":"journal-article","created":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T09:18:36Z","timestamp":1765271916000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Privacy-Preserving Driver Monitoring on the Edges: Transformer-Based Processing of Secret Shares from Video Streams"],"prefix":"10.1145","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0954-0667","authenticated-orcid":false,"given":"Tianyu","family":"Bai","sequence":"first","affiliation":[{"name":"University of North Texas","place":["Denton, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1494-5434","authenticated-orcid":false,"given":"Danyang","family":"Shao","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, University of North Texas","place":["Denton, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6456-4997","authenticated-orcid":false,"given":"Ying","family":"He","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas","place":["Denton, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0683-5848","authenticated-orcid":false,"given":"Qing","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas","place":["Denton, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6577-227X","authenticated-orcid":false,"given":"Yunhe","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas","place":["Denton, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7705-0829","authenticated-orcid":false,"given":"Song","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas","place":["Denton, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Dosovitskiy Alexey. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. Retrieved from https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_1_3_2","first-page":"103555","article-title":"Safeguarding user data privacy in online large language model services","author":"Bai Tianyu","year":"2025","unstructured":"Tianyu Bai, Yunhe Feng, and Song Fu. 2025. Safeguarding user data privacy in online large language model services. Journal of Systems Architecture. 103555.","journal-title":"Journal of Systems Architecture"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi14110316"},{"key":"e_1_3_1_5_2","first-page":"1","volume-title":"Proceedings of the 2023 32nd International Conference on Computer Communications and Networks (ICCCN)","author":"Bai Tianyu","year":"2023","unstructured":"Tianyu Bai, Danyang Shao, Ying He, Song Fu, and Qing Yang. 2023. A privacy-preserving perception framework for building vehicle-edge perception networks protecting data privacy. In Proceedings of the 2023 32nd International Conference on Computer Communications and Networks (ICCCN). IEEE, 1\u201310."},{"key":"e_1_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Tianyu Bai Qing Yang and Song Fu. 2023. User-defined privacy preserving data sharing for connected autonomous vehicles utilizing edge computing. 145\u2013157.","DOI":"10.1145\/3583740.3628436"},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1007\/3-540-46766-1_34","volume-title":"Proceedings of the Advances in Cryptology\u2014CRYPTO\u201991: Proceedings 11","author":"Beaver Donald","year":"1992","unstructured":"Donald Beaver. 1992. Efficient multiparty protocols using circuit randomization. In Proceedings of the Advances in Cryptology\u2014CRYPTO\u201991: Proceedings 11. Springer, 420\u2013432."},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23041963"},{"key":"e_1_3_1_9_2","first-page":"1287","volume-title":"Proceedings of the IEEE Intelligent Vehicles Symposium (IV)","author":"Braunagel Christian","year":"2017","unstructured":"Christian Braunagel, Enkelejda Kasneci, Wolfgang Stolzmann, and Wolfgang Rosenstiel. 2017. Driver-activity recognition in the context of conditionally autonomous driving. In Proceedings of the IEEE Intelligent Vehicles Symposium (IV). IEEE, 1287\u20131292."},{"key":"e_1_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Tianyu Chen Hangbo Bao Shaohan Huang Li Dong Binxing Jiao Daxin Jiang Haoyi Zhou Jianxin Li and Furu Wei. 2022. The-x: Privacy-preserving transformer inference with homomorphic encryption. arXiv:2206.00216. Retrieved from https:\/\/arxiv.org\/abs\/2206.00216","DOI":"10.18653\/v1\/2022.findings-acl.277"},{"key":"e_1_3_1_11_2","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1007\/11681878_15","volume-title":"Proceedings of the Theory of Cryptography Conference","author":"Damg\u00e5rd Ivan","year":"2006","unstructured":"Ivan Damg\u00e5rd, Matthias Fitzi, Eike Kiltz, Jesper Buus Nielsen, and Tomas Toft. 2006. Unconditionally secure constant-rounds multi-party computation for equality, comparison, bits and exponentiation. In Proceedings of the Theory of Cryptography Conference. Springer, 285\u2013304."},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_1_13_2","volume-title":"Proceedings of the IEEE International Conference on Parallel Processing","author":"Fu Song","year":"2005","unstructured":"Song Fu and Cheng-Zhong Xu. 2005. Service migration in distributed virtual machines for adaptive grid computing. In Proceedings of the IEEE International Conference on Parallel Processing."},{"key":"e_1_3_1_14_2","volume-title":"A Fully Homomorphic Encryption Scheme","author":"Gentry Craig","year":"2009","unstructured":"Craig Gentry. 2009. A Fully Homomorphic Encryption Scheme. Stanford University."},{"key":"e_1_3_1_15_2","volume-title":"Proceedings of the IEEE ICCV","author":"Girshick Ross","year":"2015","unstructured":"Ross Girshick. 2015. Fast r-cnn. In Proceedings of the IEEE ICCV."},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00701"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22072589"},{"issue":"16","key":"e_1_3_1_20_2","first-page":"9510","article-title":"A de-identification face recognition using extracted thermal features based on deep learning","volume":"20","author":"Lin Chih-Hsueh","year":"2020","unstructured":"Chih-Hsueh Lin, Zhi-Hao Wang, and Gwo-Jia Jong. 2020. A de-identification face recognition using extracted thermal features based on deep learning. IEEE Sensors Journal 20, 16 (2020), 9510\u20139517.","journal-title":"IEEE Sensors Journal"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.09.001"},{"key":"e_1_3_1_22_2","article-title":"Bumblebee: Secure two-party inference framework for large transformers","author":"Lu Wen-jie","year":"2023","unstructured":"Wen-jie Lu, Zhicong Huang, Zhen Gu, Jingyu Li, Jian Liu, Cheng Hong, Kui Ren, Tao Wei, and WenGuang Chen. 2023. Bumblebee: Secure two-party inference framework for large transformers. Cryptology ePrint Archive.","journal-title":"Cryptology ePrint Archive"},{"key":"e_1_3_1_23_2","article-title":"Preserving privacy in video analytics: A comprehensive review of face de-identification and background blurring techniques","author":"Maity Amit","year":"2023","unstructured":"Amit Maity, Rishi More, Gitesh Kambli, and Sarita Ambadekar. 2023. Preserving privacy in video analytics: A comprehensive review of face de-identification and background blurring techniques. Authorea Preprints.","journal-title":"Authorea Preprints"},{"key":"e_1_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Ioannis Mavromatis Andrea Tassi Giovanni Rigazzi Robert J Piechocki and Andrew Nix. 2018. Multi-radio 5G architecture for connected and autonomous vehicles: Application and design insights. arXiv:1801.09510. Retrieved from https:\/\/arxiv.org\/abs\/1801.09510","DOI":"10.4108\/eai.20-3-2018.154368"},{"key":"e_1_3_1_25_2","article-title":"THOR: Secure transformer inference with homomorphic encryption","author":"Moon Jungho","year":"2024","unstructured":"Jungho Moon, Dongwoo Yoo, Xiaoqian Jiang, and Miran Kim. 2024. THOR: Secure transformer inference with homomorphic encryption. Cryptology ePrint Archive.","journal-title":"Cryptology ePrint Archive"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.32"},{"key":"e_1_3_1_27_2","volume-title":"Proceedings of the IEEE Global Communications Conference","author":"Pannu Husanbir S.","year":"2012","unstructured":"Husanbir S. Pannu, Jianguo Liu, and Song Fu. 2012. A self-evolving anomaly detection framework for developing highly dependable utility clouds. In Proceedings of the IEEE Global Communications Conference."},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","DOI":"10.1109\/JIOT.2025.3552321","article-title":"BlindTuner: On enhancement of privacy-preserving fine-tuning of transformers based on homomorphic encryption","author":"Panzade Prajwal","year":"2025","unstructured":"Prajwal Panzade, Javad Rafiei Asl, Daniel Takabi, and Zhipeng Cai. 2025. BlindTuner: On enhancement of privacy-preserving fine-tuning of transformers based on homomorphic encryption. IEEE Internet of Things Journal 12, 19 (2025), 39211\u201339222.","journal-title":"IEEE Internet of Things Journal"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116894"},{"key":"e_1_3_1_30_2","volume-title":"Proceedings of the IEEE CVPR","author":"Redmon Joseph","year":"2016","unstructured":"Joseph Redmon, Santosh Divvala, et\u00a0al. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE CVPR."},{"key":"e_1_3_1_31_2","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems 28 (2015), 91\u201399.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/Trustcom.2015.357"},{"key":"e_1_3_1_33_2","first-page":"1814","article-title":"The PII problem: Privacy and a new concept of personally identifiable information","volume":"86","author":"Schwartz Paul M","year":"2011","unstructured":"Paul M Schwartz and Daniel J Solove. 2011. The PII problem: Privacy and a new concept of personally identifiable information. NYUL review 86 (2011), 1814.","journal-title":"NYUL review"},{"issue":"2","key":"e_1_3_1_34_2","first-page":"1","article-title":"Advanced encryption standard","volume":"6","author":"Selent Douglas","year":"2010","unstructured":"Douglas Selent. 2010. Advanced encryption standard. Rivier Academic Journal 6, 2 (2010), 1\u201314.","journal-title":"Rivier Academic Journal"},{"key":"e_1_3_1_35_2","unstructured":"Sasha Targ Diogo Almeida and Kevin Lyman. 2016. Resnet in resnet: Generalizing residual architectures. arXiv:1603.08029. Retrieved from https:\/\/arxiv.org\/abs\/1603.08029"},{"key":"e_1_3_1_36_2","volume-title":"Methodus Incrementorum Directa & Inversa","author":"Taylor Brook","year":"1717","unstructured":"Brook Taylor. 1717. Methodus Incrementorum Directa & Inversa. Inny."},{"key":"e_1_3_1_37_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar et\u00a0al. 2023. Llama: Open and efficient foundation language models. arXiv:2302.13971. Retrieved from https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_1_38_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N. Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS 2017) 30 (2017) 5998\u20136008."},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2018.2843120"},{"issue":"5","key":"e_1_3_1_40_2","first-page":"1613","article-title":"Driver drowsiness detection via multi-stream convolutional neural networks","volume":"21","author":"Weng Siyu","year":"2021","unstructured":"Siyu Weng and Shu Chien. 2021. Driver drowsiness detection via multi-stream convolutional neural networks. Sensors 21, 5 (2021), 1613.","journal-title":"Sensors"},{"key":"e_1_3_1_41_2","first-page":"14385","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wu Tianlong","year":"2023","unstructured":"Tianlong Wu, Zhuangwei Wang, Xing Zhang, Junnan Tang, Xiaojun Huang, Richard Socher, and Saining Xie. 2023. TinyViT: Fast and accurate ViT for tiny devices. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 14385\u201314395."},{"key":"e_1_3_1_42_2","volume-title":"Proceedings of the IEEE Vehicular Technology Conference","author":"Xiao Feng","year":"2024","unstructured":"Feng Xiao, Ze Xu, Yi Han, Yi Zhong, Yi Zheng, Mingxi Liao, Poshi Qin, and Yuan Wan. 2024. Machine learning based driver emotion monitoring for vehicular IoT. In Proceedings of the IEEE Vehicular Technology Conference."},{"key":"e_1_3_1_43_2","first-page":"162","volume-title":"Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence","volume":"41","author":"Zhang Xucong","year":"2017","unstructured":"Xucong Zhang, Yusuke Sugano, Mario Fritz, and Andreas Bulling. 2017. MPIIGaze: Real-world dataset and deep appearance-based gaze estimation. In Proceedings of the IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 41. 162\u2013175."},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876865"}],"container-title":["ACM Transactions on Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3777384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T16:22:46Z","timestamp":1776788566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,8,31]]}},"alternative-id":["10.1145\/3777384"],"URL":"https:\/\/doi.org\/10.1145\/3777384","relation":{},"ISSN":["2691-1914","2577-6207"],"issn-type":[{"value":"2691-1914","type":"print"},{"value":"2577-6207","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"assertion":[{"value":"2025-03-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}