{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T03:31:50Z","timestamp":1780630310222,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,18]],"date-time":"2024-11-18T00:00:00Z","timestamp":1731888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Fund for Excellent Young Scholars of Hunan Province","award":["2023JJ20076"],"award-info":[{"award-number":["2023JJ20076"]}]},{"DOI":"10.13039\/501100006374","name":"Natural Science Foundation of Hainan Province","doi-asserted-by":"publisher","award":["2021JC0004"],"award-info":[{"award-number":["2021JC0004"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Science Foundation of China","award":["62172439"],"award-info":[{"award-number":["62172439"]}]},{"name":"Central South University Innovation-Driven Research Programme","award":["2023CXQD061"],"award-info":[{"award-number":["2023CXQD061"]}]},{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFF0604504"],"award-info":[{"award-number":["2022YFF0604504"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,18]]},"DOI":"10.1145\/3691555.3696827","type":"proceedings-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T06:20:06Z","timestamp":1731997206000},"page":"13-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["A First Look At Efficient And Secure On-Device LLM Inference Against KV Leakage"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6262-9096","authenticated-orcid":false,"given":"Huan","family":"Yang","sequence":"first","affiliation":[{"name":"Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0298-7868","authenticated-orcid":false,"given":"Deyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5913-9516","authenticated-orcid":false,"given":"Yudong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Transsion CO., LTD, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1591-2526","authenticated-orcid":false,"given":"Yuanchun","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7352-8955","authenticated-orcid":false,"given":"Yunxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3214303"},{"key":"e_1_3_2_1_2_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_3_1","unstructured":"Ayoub Benaissa Bilal Retiat Bogdan Cebere and Alaa Eddine Belfedhal. 2021. TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption. arXiv:2104.03152 [cs.CR]"},{"key":"e_1_3_2_1_4_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577923.3583648"},{"key":"e_1_3_2_1_7_1","volume-title":"TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment. arXiv preprint arXiv:2404.11121","author":"Li Qinfeng","year":"2024","unstructured":"Qinfeng Li, Zhiqiang Shen, Zhenghan Qin, Yangfan Xie, Xuhong Zhang, Tianyu Du, and Jianwei Yin. 2024. TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment. arXiv preprint arXiv:2404.11121 (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41635-018-0039-0"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3386901.3388946"},{"key":"e_1_3_2_1_10_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in PyTorch. (2017)."},{"key":"e_1_3_2_1_11_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_13_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_14_1","volume-title":"LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory. arXiv preprint arXiv:2401.16603","author":"Sorensen Tyler","year":"2024","unstructured":"Tyler Sorensen and Heidy Khlaaf. 2024. LeftoverLocals: Listening to LLM Responses Through Leaked GPU Local Memory. arXiv preprint arXiv:2401.16603 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP46215.2023.10179382"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.34740\/KAGGLE\/M\/3301"},{"key":"e_1_3_2_1_17_1","unstructured":"GLM Team Aohan Zeng Bin Xu Bowen Wang Chenhui Zhang Da Yin Diego Rojas Guanyu Feng Hanlin Zhao Hanyu Lai et al. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. arXiv e-prints (2024) arXiv-2406."},{"key":"e_1_3_2_1_18_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv:2302.13971 [cs.CL]"},{"key":"e_1_3_2_1_19_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","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. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_20_1","volume-title":"Mengwei Xu and Xuanzhe Liu","author":"Wangsong Yin Yuanchun Li","year":"2024","unstructured":"Yuanchun Li Wangsong Yin, Mengwei Xu and Xuanzhe Liu. 2024. LLM as a System Service on Mobile Devices. arXiv prepring arXiv:2403.11805 (2024)."},{"key":"e_1_3_2_1_21_1","unstructured":"Zama. 2022. Concrete ML: a Privacy-Preserving Machine Learning Library using Fully Homomorphic Encryption for Data Scientists. https:\/\/github.com\/zama-ai\/concrete-ml."},{"key":"e_1_3_2_1_22_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."}],"event":{"name":"ACM MobiCom '24: The 30th Annual International Conference on Mobile Computing and Networking","location":"Washington D.C. DC USA","acronym":"ACM MobiCom '24","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the Workshop on Mobility in the Evolving Internet Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691555.3696827","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3691555.3696827","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T12:44:44Z","timestamp":1756212284000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691555.3696827"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,18]]},"references-count":22,"alternative-id":["10.1145\/3691555.3696827","10.1145\/3691555"],"URL":"https:\/\/doi.org\/10.1145\/3691555.3696827","relation":{},"subject":[],"published":{"date-parts":[[2024,11,18]]},"assertion":[{"value":"2024-11-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}