{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:17:16Z","timestamp":1777421836732,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"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":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3691621.3694952","type":"proceedings-article","created":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T12:18:59Z","timestamp":1729599539000},"page":"208-217","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A First Look at LLM-powered Smartphones"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8116-1681","authenticated-orcid":false,"given":"Liangxuan","family":"Wu","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8793-5367","authenticated-orcid":false,"given":"Yanjie","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8117-0352","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5216-933X","authenticated-orcid":false,"given":"Tianming","family":"Liu","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1100-8633","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2020.02.002"},{"key":"e_1_3_2_1_2_1","volume-title":"A comprehensive analysis of the android permissions system. Ieee access 8","author":"Almomani Iman M","year":"2020","unstructured":"Iman M Almomani and Aala Al Khayer. 2020. A comprehensive analysis of the android permissions system. Ieee access 8 (2020), 216671--216688."},{"key":"e_1_3_2_1_3_1","unstructured":"Apple. 2024. Apple Intelligence. https:\/\/www.apple.com\/apple-intelligence\/"},{"key":"e_1_3_2_1_4_1","volume-title":"Apple Intelligence Foundation Language Models. arXiv preprint arXiv:2407.21075","year":"2024","unstructured":"Apple. 2024. Apple Intelligence Foundation Language Models. arXiv preprint arXiv:2407.21075 (2024)."},{"key":"e_1_3_2_1_5_1","unstructured":"Cambricon Technologies Corporation Limited. 2024. Cambricon Official Website. https:\/\/www.cambricon.com\/ Accessed on [insert access date]."},{"key":"e_1_3_2_1_6_1","volume-title":"LLM for Mobile: An Initial Roadmap. arXiv preprint arXiv:2407.06573","author":"Chen Daihang","year":"2024","unstructured":"Daihang Chen, Yonghui Liu, Mingyi Zhou, Yanjie Zhao, Haoyu Wang, Shuai Wang, Xiao Chen, Tegawend\u00e9 F Bissyand\u00e9, Jacques Klein, and Li Li. 2024. LLM for Mobile: An Initial Roadmap. arXiv preprint arXiv:2407.06573 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2548426"},{"key":"e_1_3_2_1_8_1","volume-title":"Eric Lehman, Caiming Xiong, Richard Socher, and Byron C Wallace.","author":"DeYoung Jay","year":"2019","unstructured":"Jay DeYoung, Sarthak Jain, Nazneen Fatema Rajani, Eric Lehman, Caiming Xiong, Richard Socher, and Byron C Wallace. 2019. ERASER: A benchmark to evaluate rationalized NLP models. arXiv preprint arXiv:1911.03429 (2019)."},{"key":"e_1_3_2_1_9_1","volume-title":"International colloquium on automata, languages, and programming","author":"Dwork Cynthia","unstructured":"Cynthia Dwork. 2006. Differential privacy. In International colloquium on automata, languages, and programming. Springer, 1--12."},{"key":"e_1_3_2_1_10_1","unstructured":"Deep Ganguli Liane Lovitt Jackson Kernion Amanda Askell Yuntao Bai Saurav Kadavath Ben Mann Ethan Perez Nicholas Schiefer Kamal Ndousse et al. 2022. Red teaming language models to reduce harms: Methods scaling behaviors and lessons learned. arXiv preprint arXiv:2209.07858 (2022)."},{"key":"e_1_3_2_1_11_1","unstructured":"Google. 2024. Pixel 9 pro. https:\/\/store.google.com\/gb\/product\/pixel_9_pro"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_13_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_14_1","unstructured":"HONOR. 2024. MagicOS. https:\/\/www.honor.com\/global\/magic-os\/"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Xinyi Hou Yanjie Zhao Yue Liu Zhou Yang Kailong Wang Li Li Xiapu Luo David Lo John Grundy and Haoyu Wang. 2024. Large Language Models for Software Engineering: A Systematic Literature Review. arXiv:2308.10620 [cs.SE] https:\/\/arxiv.org\/abs\/2308.10620","DOI":"10.1145\/3695988"},{"key":"e_1_3_2_1_16_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Bias assessment and mitigation in llm-based code generation. arXiv preprint arXiv:2309.14345","author":"Huang Dong","year":"2023","unstructured":"Dong Huang, Qingwen Bu, Jie Zhang, Xiaofei Xie, Junjie Chen, and Heming Cui. 2023. Bias assessment and mitigation in llm-based code generation. arXiv preprint arXiv:2309.14345 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2020.100270"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00447"},{"key":"e_1_3_2_1_20_1","volume-title":"Prompting Large Language Models with Audio for General-Purpose Speech Summarization. arXiv preprint arXiv:2406.05968","author":"Kang Wonjune","year":"2024","unstructured":"Wonjune Kang and Deb Roy. 2024. Prompting Large Language Models with Audio for General-Purpose Speech Summarization. arXiv preprint arXiv:2406.05968 (2024)."},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 6710--6720","author":"Kong Rui","year":"2024","unstructured":"Rui Kong, Yuanchun Li, Qingtian Feng, Weijun Wang, Xiaozhou Ye, Ye Ouyang, Linghe Kong, and Yunxin Liu. 2024. SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 6710--6720."},{"key":"e_1_3_2_1_22_1","volume-title":"Transformer-lite: High-efficiency deployment of large language models on mobile phone gpus. arXiv preprint arXiv:2403.20041","author":"Li Luchang","year":"2024","unstructured":"Luchang Li, Sheng Qian, Jie Lu, Lunxi Yuan, Rui Wang, and Qin Xie. 2024. Transformer-lite: High-efficiency deployment of large language models on mobile phone gpus. arXiv preprint arXiv:2403.20041 (2024)."},{"key":"e_1_3_2_1_23_1","first-page":"87","article-title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. Proceedings of Machine Learning and Systems 6 (2024), 87--100.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. 2115--2128","author":"Liu Yupei","year":"2022","unstructured":"Yupei Liu, Jinyuan Jia, Hongbin Liu, and Neil Zhenqiang Gong. 2022. Stolenencoder: stealing pre-trained encoders in self-supervised learning. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. 2115--2128."},{"key":"e_1_3_2_1_25_1","volume-title":"Opportunities, Challenges, and Design Guidelines. arXiv preprint arXiv:2309.13879","author":"Mahmood Amama","year":"2023","unstructured":"Amama Mahmood, Junxiang Wang, Bingsheng Yao, Dakuo Wang, and Chien-Ming Huang. 2023. LLM-Powered Conversational Voice Assistants: Interaction Patterns, Opportunities, Challenges, and Design Guidelines. arXiv preprint arXiv:2309.13879 (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, et al.","author":"Mehta Sachin","year":"2024","unstructured":"Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao, Maxwell Horton, Yanzi Jin, Chenfan Sun, Iman Mirzadeh, Mahyar Najibi, Dmitry Belenko, Peter Zatloukal, et al. 2024. OpenELM: An Efficient Language Model Family with Open-source Training and Inference Framework. arXiv preprint arXiv:2404.14619 (2024)."},{"key":"e_1_3_2_1_27_1","unstructured":"Paulius Micikevicius Sharan Narang Jonah Alben Gregory Diamos Erich Elsen David Garcia Boris Ginsburg Michael Houston Oleksii Kuchaiev Ganesh Venkatesh et al. 2017. Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/997150.997156"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. 1835--1849","author":"Naseh Ali","year":"2023","unstructured":"Ali Naseh, Kalpesh Krishna, Mohit Iyyer, and Amir Houmansadr. 2023. Stealing the decoding algorithms of language models. In Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. 1835--1849."},{"key":"e_1_3_2_1_30_1","unstructured":"OPPO. 2024. ColorOS 14. https:\/\/www.coloros.com\/version\/coloros14\/"},{"key":"e_1_3_2_1_31_1","volume-title":"PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs. arXiv preprint arXiv:2407.01031","author":"Peng Dan","year":"2024","unstructured":"Dan Peng, Zhihui Fu, and Jun Wang. 2024. PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs. arXiv preprint arXiv:2407.01031 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices. arXiv preprint arXiv:2406.03777","author":"Qin Ruiyang","year":"2024","unstructured":"Ruiyang Qin, Dancheng Liu, Zheyu Yan, Zhaoxuan Tan, Zixuan Pan, Zhenge Jia, Meng Jiang, Ahmed Abbasi, Jinjun Xiong, and Yiyu Shi. 2024. Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices. arXiv preprint arXiv:2406.03777 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey. arXiv preprint arXiv:2407.18921","author":"Qu Guanqiao","year":"2024","unstructured":"Guanqiao Qu, Qiyuan Chen, Wei Wei, Zheng Lin, Xianhao Chen, and Kaibin Huang. 2024. Mobile Edge Intelligence for Large Language Models: A Contemporary Survey. arXiv preprint arXiv:2407.18921 (2024)."},{"key":"e_1_3_2_1_34_1","volume-title":"Jingbo Zhou, Mark Tehranipoor, and Farimah Farahmandi.","author":"Saha Dipayan","year":"2024","unstructured":"Dipayan Saha, Shams Tarek, Katayoon Yahyaei, Sujan Kumar Saha, Jingbo Zhou, Mark Tehranipoor, and Farimah Farahmandi. 2024. Llm for soc security: A paradigm shift. IEEE Access (2024)."},{"key":"e_1_3_2_1_35_1","unstructured":"Samsung. 2024. Galaxy AI is here. https:\/\/www.samsung.com\/us\/galaxy-ai"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iotcps.2023.02.004"},{"key":"e_1_3_2_1_37_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Justin Svegliato, Luke Bailey, Tiffany Wang, Isaac Ong, Karim Elmaaroufi, Pieter Abbeel, Trevor Darrell, et al.","author":"Toyer Sam","year":"2023","unstructured":"Sam Toyer, Olivia Watkins, Ethan Adrian Mendes, Justin Svegliato, Luke Bailey, Tiffany Wang, Isaac Ong, Karim Elmaaroufi, Pieter Abbeel, Trevor Darrell, et al. 2023. Tensor trust: Interpretable prompt injection attacks from an online game. arXiv preprint arXiv:2311.01011 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2014.126"},{"key":"e_1_3_2_1_40_1","unstructured":"vivo. 2024. Origin OS. https:\/\/www.vivo.com.cn\/originos"},{"key":"e_1_3_2_1_41_1","volume-title":"Understanding User Experience in Large Language Model Interactions. arXiv preprint arXiv:2401.08329","author":"Wang Jiayin","year":"2024","unstructured":"Jiayin Wang, Weizhi Ma, Peijie Sun, Min Zhang, and Jian-Yun Nie. 2024. Understanding User Experience in Large Language Model Interactions. arXiv preprint arXiv:2401.08329 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"Pandora's White-Box: Increased Training Data Leakage in Open LLMs. arXiv preprint arXiv:2402.17012","author":"Wang Jeffrey G","year":"2024","unstructured":"Jeffrey G Wang, Jason Wang, Marvin Li, and Seth Neel. 2024. Pandora's White-Box: Increased Training Data Leakage in Open LLMs. arXiv preprint arXiv:2402.17012 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems 36","author":"Wei Alexander","year":"2024","unstructured":"Alexander Wei, Nika Haghtalab, and Jacob Steinhardt. 2024. Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_44_1","unstructured":"Xiaomi. 2024. Xiaomi 14 Ultra. https:\/\/www.mi.com\/prod\/xiaomi-14-ultra"},{"key":"e_1_3_2_1_45_1","volume-title":"LLM Jailbreak Attack versus Defense Techniques-A Comprehensive Study. arXiv preprint arXiv:2402.13457","author":"Xu Zihao","year":"2024","unstructured":"Zihao Xu, Yi Liu, Gelei Deng, Yuekang Li, and Stjepan Picek. 2024. LLM Jailbreak Attack versus Defense Techniques-A Comprehensive Study. arXiv preprint arXiv:2402.13457 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Trojllm: A black-box trojan prompt attack on large language models. Advances in Neural Information Processing Systems 36","author":"Xue Jiaqi","year":"2024","unstructured":"Jiaqi Xue, Mengxin Zheng, Ting Hua, Yilin Shen, Yepeng Liu, Ladislau B\u00f6l\u00f6ni, and Qian Lou. 2024. Trojllm: A black-box trojan prompt attack on large language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_47_1","volume-title":"PowerInfer-2: Fast Large Language Model Inference on a Smartphone. arXiv preprint arXiv:2406.06282","author":"Xue Zhenliang","year":"2024","unstructured":"Zhenliang Xue, Yixin Song, Zeyu Mi, Le Chen, Yubin Xia, and Haibo Chen. 2024. PowerInfer-2: Fast Large Language Model Inference on a Smartphone. arXiv preprint arXiv:2406.06282 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Llm as a system service on mobile devices. arXiv preprint arXiv:2403.11805","author":"Yin Wangsong","year":"2024","unstructured":"Wangsong Yin, Mengwei Xu, Yuanchun Li, and Xuanzhe Liu. 2024. Llm as a system service on mobile devices. arXiv preprint arXiv:2403.11805 (2024)."},{"key":"e_1_3_2_1_49_1","volume-title":"International Conference on Machine Learning. PMLR, 40306--40320","author":"Yu Weichen","year":"2023","unstructured":"Weichen Yu, Tianyu Pang, Qian Liu, Chao Du, Bingyi Kang, Yan Huang, Min Lin, and Shuicheng Yan. 2023. Bag of tricks for training data extraction from language models. In International Conference on Machine Learning. PMLR, 40306--40320."},{"key":"e_1_3_2_1_50_1","volume-title":"Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis. 1005--1017","author":"Zhou Mingyi","year":"2023","unstructured":"Mingyi Zhou, Xiang Gao, Jing Wu, John Grundy, Xiao Chen, Chunyang Chen, and Li Li. 2023. Modelobfuscator: Obfuscating model information to protect deployed ml-based systems. In Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis. 1005--1017."}],"event":{"name":"ASEW '24: 39th IEEE\/ACM International Conference on Automated Software Engineering Workshops","location":"Sacramento CA USA","acronym":"ASEW '24","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS"]},"container-title":["Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering Workshops"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691621.3694952","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:09:40Z","timestamp":1750295380000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3691621.3694952"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":50,"alternative-id":["10.1145\/3691621.3694952","10.1145\/3691621"],"URL":"https:\/\/doi.org\/10.1145\/3691621.3694952","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2024-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}