{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:36:44Z","timestamp":1768073804181,"version":"3.49.0"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Sen. Netw."],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>End-edge collaborative inference enhances computational efficiency by segmenting a deep neural network (DNN) model into two parts, executed across the end device and the edge node. However, existing collaborative inference strategies often involve transmitting original inputs from the end device to the edge node, resulting in significant risks of user detail leakage without requiring input reconstruction. Therefore, in this work, we present SecoInfer, a secure layer-level DNN end-edge collaborative inference framework. SecoInfer achieves joint optimization of data privacy and inference latency for DNN partition solutions that meet latency constraints, supported by three key designs. First, the privacy-aware DNN layer projection measurement quantifies the difficulty adversaries encounter in reconstructing the original input from the intermediate output of each layer. Then, the latency-privacy integrated structure modeling enables the direct calculation of the privacy measurement and inference latency for each partition solution from a list element or a directed acyclic graph (DAG) cut. Finally, the two-stage latency constraint adjustment scheme narrows down the search space of feasible partition solutions at the block level and fine-tunes the final one to meet the latency constraint based on layer depth. We prototype SecoInfer, utilizing a Raspberry Pi 4B as the end device and a server with an NVIDIA GeForce RTX 3060 GPU as the edge node. Experimental results demonstrate that under latency constraints of 20 ms, 33 ms, and 40 ms, SecoInfer reduces adversarial data reconstruction by 9.84%, 19.26%, and 25.18%, respectively, without any loss of task model accuracy. SecoInfer also enhances efficiency, reducing the time needed to determine optimal end-edge partition solutions on a Raspberry Pi 4B by 18.04%.<\/jats:p>","DOI":"10.1145\/3694972","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T11:14:48Z","timestamp":1728558888000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SecoInfer: Secure DNN End-Edge Collaborative Inference Framework Optimizing Privacy and Latency"],"prefix":"10.1145","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7433-3145","authenticated-orcid":false,"given":"Yunhao","family":"Yao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3340-8585","authenticated-orcid":false,"given":"Jiahui","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3603-3886","authenticated-orcid":false,"given":"Guangyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9670-0196","authenticated-orcid":false,"given":"Yihang","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2624-8755","authenticated-orcid":false,"given":"Mu","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6885-1185","authenticated-orcid":false,"given":"Puhan","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0398-2631","authenticated-orcid":false,"given":"Zhiqiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-6625","authenticated-orcid":false,"given":"Xiang-Yang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"2009. CIFAR-10 - Canadian Institute For Advanced Research. Retrieved from https:\/\/www.cs.toronto.edu\/kriz\/cifar.html"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Ahmad AlTwaijiry. 2021. Cloud computing present limitations and future trends. Scholarlib Computer Science Review 1 1 (2021) 1\u201320.","DOI":"10.14293\/S2199-1006.1.SOR-.PPEYYII.v1"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467078"},{"key":"e_1_3_2_5_2","first-page":"1597","volume-title":"International Conference on Machine Learning","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning. PMLR, 1597\u20131607."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12262"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD50377.2020.00055"},{"issue":"7","key":"e_1_3_2_8_2","first-page":"1665","article-title":"Model parallelism optimization for distributed inference via decoupled CNN structure","volume":"32","author":"Du Jiangsu","year":"2020","unstructured":"Jiangsu Du, Xin Zhu, Minghua Shen, Yunfei Du, Yutong Lu, Nong Xiao, and Xiangke Liao. 2020. Model parallelism optimization for distributed inference via decoupled CNN structure. IEEE Transactions on Parallel and Distributed Systems 32, 7 (2020), 1665\u20131676.","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.14778\/2732286.2732289"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-95729-6_10"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_13_2","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770\u2013778."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3359789.3359824"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3022358"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737614"},{"key":"e_1_3_2_17_2","unstructured":"H. Hu. 2016. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250 (2016)."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_2_19_2","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25 (2012)."},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_2_21_2","article-title":"MNIST handwritten digit database","author":"LeCun Yann","year":"2010","unstructured":"Yann LeCun, Corinna Cortes, and CJ Burges. 2010. MNIST handwritten digit database. AT&T Labs [Online]. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist (2010).","journal-title":"AT&T Labs [Online]. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946140"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"e_1_3_2_25_2","unstructured":"Jian-Hao Luo and Jianxin Wu. 2017. An entropy-based pruning method for cnn compression. arXiv preprint arXiv:1706.05791 (2017)."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927211"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203852"},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Vahid Mirjalili Sebastian Raschka and Arun Ross. 2020. PrivacyNet: Semi-adversarial networks for multi-attribute face privacy. IEEE Transactions on Image Processing 29 (2020) 9400\u20139412.","DOI":"10.1109\/TIP.2020.3024026"},{"key":"e_1_3_2_29_2","unstructured":"Pavlo Molchanov Stephen Tyree Tero Karras Timo Aila and Jan Kautz. 2022. Pruning convolutional neural networks for resource efficient inference. In International Conference on Learning Representations."},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01246"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00269"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(92)90242-F"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"e_1_3_2_34_2","unstructured":"K. Simonyan and A. Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations (ICLR 2015) Computational."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01195"},{"key":"e_1_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Christian Szegedy Wei Liu Yangqing Jia Pierre Sermanet Scott Reed Dragomir Anguelov Dumitru Erhan Vincent Vanhoucke and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_3_2_38_2","unstructured":"Florian Tramer Alexey Kurakin Nicolas Papernot Ian Goodfellow Dan Boneh and Patrick McDaniel. 2018. Ensemble adversarial training: Attacks and defenses. In International Conference on Learning Representations."},{"key":"e_1_3_2_39_2","unstructured":"International Telecommunication Union. 2003. ITU-T Recommendation G.114: One-way Transmission Time. Retrieved from https:\/\/www.itu.int\/rec\/T-REC-G.114Accessed: 2024-05-30."},{"key":"e_1_3_2_40_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","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. In Advances in Neural Information Processing Systems. 5998\u20136008."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Guangyu Wu Fuhui Zhou Guoru Ding Qihui Wu and Xiang-Yang Li. 2022. An efficient heterogeneous edge-cloud learning framework for spectrum data compression. IEEE Transactions on Mobile Computing 22 7 (2022) 3823\u20133839.","DOI":"10.1109\/TMC.2022.3153049"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Guangyu Wu Fuhui Zhou Chengzhen Meng and Xiang-Yang Li. 2024. Precise UAV MMW-Vision positioning: A modal-oriented self-tuning fusion framework. IEEE Journal on Selected Areas in Communications 42 1 (2024) 6\u201320.","DOI":"10.1109\/JSAC.2023.3322851"},{"key":"e_1_3_2_44_2","unstructured":"Guangyu Wu Fuhui Zhou Yuben Qu Puhan Luo and Xiang-Yang Li. 2023. QoS-ensured model optimization for AIoT: A multi-scale reinforcement learning approach. IEEE Transactions on Mobile Computing 1 (2023) 1\u201318."},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2893250"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS51616.2021.00011"},{"key":"e_1_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Dayong Ye Sheng Shen Tianqing Zhu Bo Liu and Wanlei Zhou. 2022. One parameter defense.defending against data inference attacks via differential privacy. IEEE Transactions on Information Forensics and Security 17 (2022) 1466\u20131480.","DOI":"10.1109\/TIFS.2022.3163591"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517016"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i9.21180"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604825"},{"key":"e_1_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Jun Zhang Zhenjie Zhang Xiaokui Xiao Yin Yang and Marianne Winslett. 2012. Functional mechanism: regression analysis under differential privacy. Proceedings of the VLDB Endowment 5 11 (2012) 1364\u20131375.","DOI":"10.14778\/2350229.2350253"},{"issue":"2","key":"e_1_3_2_52_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3397315","article-title":"Towards real-time cooperative deep inference over the cloud and edge end devices","volume":"4","author":"Zhang Shigeng","year":"2020","unstructured":"Shigeng Zhang, Yinggang Li, Xuan Liu, Song Guo, Weiping Wang, Jianxin Wang, Bo Ding, and Di Wu. 2020. Towards real-time cooperative deep inference over the cloud and edge end devices. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 2 (2020), 1\u201324.","journal-title":"Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3058532"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404473"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00033"},{"key":"e_1_3_2_56_2","doi-asserted-by":"crossref","unstructured":"Lingchen Zhao Qian Wang Qin Zou Yan Zhang and Yanjiao Chen. 2020. Privacy-preserving collaborative deep learning with unreliable participants. IEEE Transactions on Information Forensics and Security 15 (2020) 1486\u20131500.","DOI":"10.1109\/TIFS.2019.2939713"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858384"}],"container-title":["ACM Transactions on Sensor Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694972","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3694972","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694972"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"references-count":56,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3694972"],"URL":"https:\/\/doi.org\/10.1145\/3694972","relation":{},"ISSN":["1550-4859","1550-4867"],"issn-type":[{"value":"1550-4859","type":"print"},{"value":"1550-4867","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"2023-12-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-01","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}