{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T21:28:33Z","timestamp":1763501313579,"version":"3.45.0"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"4","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62402027, 62472023"],"award-info":[{"award-number":["62402027, 62472023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2025JBMC013"],"award-info":[{"award-number":["2025JBMC013"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Things"],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>Accurately perceiving service states of the Internet of Things (IoT) is crucial for maintaining system stability and long-term sustainability. Recently, Large Language Models (LLMs) have emerged as a novel technological advancement, offering unprecedented possibilities in various domains due to their advanced comprehension capabilities. However, the limited data availability problem poses a challenge to the integration of domain knowledge into LLMs and the enhancement of their ability to perceive service states. In this article, a novel adversarial augmentation-based domain LLM framework for IoT services is proposed to solve this problem. We first construct an LLM fine-tuning dataset through an elaborate hierarchical prompt template, which integrates task-specific instructions, heterogeneous service data, and statistical features to the service contextual description. Then, inspired by using specialized compact small-models to enhance the capabilities of LLMs, we design two dedicated domain-specific small-models, including a service topology prediction model and a running status prediction model, to capture evolution patterns of services from different perspectives. On this basis, we design an LLM fine-tuning framework based on the domain adversarial distillation, which comprises an LLM parameter tuning module and a small-model adversarial distillation module. The former leverages the Low-Rank Adaptation (LoRA) algorithm to fine-tune the LLM. The latter distills the domain knowledge of small-models into the LLM through aligning the latent vector distributions of the LLM with those of small-models. Following the adversarial training, the LLM will be equipped with domain capabilities of small-models. Experimental results on two datasets demonstrate the effectiveness of our LLM framework.<\/jats:p>","DOI":"10.1145\/3762668","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:51:31Z","timestamp":1755863491000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Novel Adversarial Augmentation-based Domain LLM Framework for Perceiving IoT Service States"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0390-5449","authenticated-orcid":false,"given":"Peng","family":"Qi","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Beijing Jiaotong University","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5029-0091","authenticated-orcid":false,"given":"Zuodong","family":"Jin","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7368-2132","authenticated-orcid":false,"given":"Dan","family":"Tao","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University","place":["Beijing, China"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2490-6654","authenticated-orcid":false,"given":"Ruipeng","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University","place":["Beijing, China"]}]}],"member":"320","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"e_1_3_1_2_2","article-title":"Number of Internet of Things (IoT) connections worldwide from 2022 to 2023, with forecasts from 2024 to 2033","author":"Vailshery Lionel Sujay","year":"2024","unstructured":"Lionel Sujay Vailshery. 2024. Number of Internet of Things (IoT) connections worldwide from 2022 to 2023, with forecasts from 2024 to 2033. Retrieved from https:\/\/www.statista.com\/statistics\/1183457\/iot-connected-devices-worldwide\/. (2024).","journal-title":"R"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100048"},{"key":"e_1_3_1_4_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv:2407.21783. Retrieved from https:\/\/arxiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_1_5_2","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et\u00a0al. 2024. Qwen2. 5 technical report. arXiv:2412.15115. Retrieved from https:\/\/arxiv.org\/abs\/2412.15115 (2024)."},{"key":"e_1_3_1_6_2","first-page":"522","volume-title":"Proceedings of the Conference on Health, Inference, and Learning","author":"Kim Yubin","year":"2024","unstructured":"Yubin Kim, Xuhai Xu, Daniel McDuff, Cynthia Breazeal, and Hae Won Park. 2024. Health-LLM: Large language models for health prediction via wearable sensor data. In Proceedings of the Conference on Health, Inference, and Learning. PMLR, 522\u2013539."},{"key":"e_1_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Dat Mai. 2024. Stockgpt: A genai model for stock prediction and trading. arXiv:2404.05101. Retrieved from https:\/\/arxiv.org\/abs\/2404.05101 (2024).","DOI":"10.2139\/ssrn.4787199"},{"key":"e_1_3_1_8_2","unstructured":"Xiang Li Zhenyu Li Chen Shi Yong Xu Qing Du Mingkui Tan and Jun Huang. 2024. AlphaFin: Benchmarking financial analysis with retrieval-augmented stock-chain framework. In Proceedings of the 2024 Joint International Conference on Computational Linguistics Language Resources and Evaluation (LREC-COLING 2024). 773\u2013783."},{"key":"e_1_3_1_9_2","unstructured":"Mengxi Xie. 2024. Why the \u201cbig Model\u201d landing performance is inferior to the \u201csmall model\u201d. (2024).Retrieved from https:\/\/news.sjtu.edu.cn\/mtjj\/20240116\/193173.html"},{"key":"e_1_3_1_10_2","unstructured":"Yu. 2024. In the age of big models are small models still necessary? (2024).Retrieved from https:\/\/news.sjtu.edu.cn\/mtjj\/20240116\/193173.html"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599766"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3679854"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3629526.3645047"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.03.020"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05659-5"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796778"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.3390\/su131810057"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2024.124378"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2024.3358730"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27764"},{"key":"e_1_3_1_21_2","unstructured":"Baian Chen Chang Shu Ehsan Shareghi Nigel Collier Karthik Narasimhan and Shunyu Yao. 2023. Fireact: Toward language agent fine-tuning. arXiv:2310.05915. Retrieved from https:\/\/arxiv.org\/abs\/2310.05915 (2023)."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26505"},{"key":"e_1_3_1_23_2","unstructured":"Yixiao Li Yifan Yu Chen Liang Pengcheng He Nikos Karampatziakis Weizhu Chen and Tuo Zhao. 2023. Loftq: Lora-fine-tuning-aware quantization for large language models. arXiv:2310.08659. Retrieved from https:\/\/arxiv.org\/abs\/2310.08659 (2023)."},{"key":"e_1_3_1_24_2","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36 (2023) 10088\u201310115."},{"key":"e_1_3_1_25_2","unstructured":"Ruidan He Linlin Liu Hai Ye Qingyu Tan Bosheng Ding Liying Cheng Jiawei Low Lidong Bing and Luo Si. 2021. On the effectiveness of adapter-based tuning for pretrained language model adaptation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2208\u20132222."},{"key":"e_1_3_1_26_2","doi-asserted-by":"crossref","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 4582\u20134597.","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96530-3"},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Xiao Liu Kaixuan Ji Yicheng Fu Weng Tam Zhengxiao Du Zhilin Yang and Jie Tang. 2022. P-Tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 61\u201368.","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_1_29_2","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531 (2015)."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657692"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"e_1_3_1_32_2","first-page":"1607","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Furlanello Tommaso","year":"2018","unstructured":"Tommaso Furlanello, Zachary Lipton, Michael Tschannen, Laurent Itti, and Anima Anandkumar. 2018. Born again neural networks. In Proceedings of the International Conference on Machine Learning. PMLR, 1607\u20131616."},{"key":"e_1_3_1_33_2","unstructured":"Adriana Romero Nicolas Ballas Samira Ebrahimi Kahou Antoine Chassang Carlo Gatta and Yoshua Bengio. 2014. Fitnets: Hints for thin deep nets. arXiv:1412.6550. Retrieved from https:\/\/arxiv.org\/abs\/1412.6550 (2014)."},{"key":"e_1_3_1_34_2","unstructured":"Jangho Kim SeongUk Park and Nojun Kwak. 2018. Paraphrasing complex network: Network compression via factor transfer. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2765\u20132774."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"e_1_3_1_36_2","unstructured":"Sergey Zagoruyko and Nikos Komodakis. 2017. Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. In International Conference on Learning Representations."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2024.112127"},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Yufeng Wang Ziyan Lu Jianhua Ma and Qun Jin. 2025. Locational false data injection attack detection in smart grid using recursive variational graph autoencoder. IEEE Internet of Things Journal 12 10 (2025) 13697\u201313708.","DOI":"10.1109\/JIOT.2025.3526672"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108308"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3077537"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2023.1211739"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2024.112145"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.2991\/ncce-18.2018.69"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2899395"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.06.024"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ad07b6"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127680"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2883647"},{"key":"e_1_3_1_51_2","article-title":"GC-LSTM: Graph convolution embedded LSTM for dynamic network link prediction","author":"Chen Jinyin","year":"2022","unstructured":"Jinyin Chen, Xueke Wang, and Xuanheng Xu. 2022. GC-LSTM: Graph convolution embedded LSTM for dynamic network link prediction. Applied Intelligence 52, 7 (2022), 7513\u20137528.","journal-title":"Applied Intelligence"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3159661"},{"key":"e_1_3_1_53_2","unstructured":"Hamzah A. A. M. Qaid Bo Zhang Dan Li See-Kiong Ng and Wei Li. 2024. FD-LLM: Large Language Model for Fault Diagnosis of Machines. arXiv:2412.01218. Retrieved from https:\/\/arxiv.org\/abs\/2412.01218 (2024)."},{"key":"e_1_3_1_54_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171\u20134186."}],"container-title":["ACM Transactions on Internet of Things"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3762668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T21:23:07Z","timestamp":1763500987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3762668"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":53,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3762668"],"URL":"https:\/\/doi.org\/10.1145\/3762668","relation":{},"ISSN":["2691-1914","2577-6207"],"issn-type":[{"type":"print","value":"2691-1914"},{"type":"electronic","value":"2577-6207"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"2025-02-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-12","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}