{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T04:13:53Z","timestamp":1769919233578,"version":"3.49.0"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T00:00:00Z","timestamp":1735171200000},"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. Intell. Syst. Technol."],"published-print":{"date-parts":[[2025,2,28]]},"abstract":"<jats:p>Decentralized machine learning, such as Federated Learning (FL), is widely adopted in many application domains. Especially in domains like recommendation systems, sharing gradients instead of private data has recently caught the research community\u2019s attention. Personalized travel route recommendation utilizes users\u2019 location data to recommend optimal travel routes. Location data is extremely privacy sensitive, presenting increased risks of exposing behavioral patterns and demographic attributes. FL for route recommendation can mitigate the sharing of location data. However, this article shows that an adversary can recover the user trajectories used to train the federated recommendation models with high proximity accuracy. To this effect, we propose a novel attack called DeepSneak, which uses shared gradients obtained from global model training in FL to reconstruct private user trajectories. We formulate the attack as a regression problem and train a generative model by minimizing the distance between gradients. We validate the success of DeepSneak on two real-world trajectory datasets. The results show that we can recover the location trajectories of users with reasonable spatial and semantic accuracy.<\/jats:p>","DOI":"10.1145\/3670412","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T16:28:36Z","timestamp":1721665716000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DeepSneak: User GPS Trajectory Reconstruction from Federated Route Recommendation Models"],"prefix":"10.1145","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6871-3304","authenticated-orcid":false,"given":"Thirasara","family":"Ariyarathna","sequence":"first","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0619-6361","authenticated-orcid":false,"given":"Meisam","family":"Mohommady","sequence":"additional","affiliation":[{"name":"Iowa State University, Ames, Iowa, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4425-7388","authenticated-orcid":false,"given":"Hye-young","family":"Paik","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1835-3475","authenticated-orcid":false,"given":"Salil S.","family":"Kanhere","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,26]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2505395.2505398"},{"key":"e_1_3_2_4_2","first-page":"214","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Arjovsky Martin","year":"2017","unstructured":"Martin Arjovsky, Soumith Chintala, and L\u00e9on Bottou. 2017. Wasserstein generative adversarial networks. In Proceedings of the International Conference on Machine Learning. PMLR, 214\u2013223."},{"key":"e_1_3_2_5_2","unstructured":"Dawei Chen Cheng Soon Ong and Lexing Xie. 2016. Learning points and routes to recommend trajectories. arXiv:1608.07051. Retrieved from http:\/\/arxiv.org\/abs\/1608.07051"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2011.5767890"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2017.1326535"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113313"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02011-7_13"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2190726"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2660267.2660270"},{"key":"e_1_3_2_12_2","unstructured":"OpenStreetMap Foundation. 2023. OpenStreetMap. Retrieved from https:\/\/www.openstreetmap.org\/"},{"key":"e_1_3_2_13_2","first-page":"16937","volume-title":"Proceedings of the Advances in Neural Information Processing Systems,","volume":"33","author":"Geiping Jonas","year":"2020","unstructured":"Jonas Geiping, Hartmut Bauermeister, Hannah Dr\u00f6ge, and Michael Moeller. 2020. Inverting gradients-how easy is it to break privacy in federated learning? In Proceedings of the Advances in Neural Information Processing Systems, Vol. 33, 16937\u201316947."},{"key":"e_1_3_2_14_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems,","volume":"27","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 27."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560486"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2006.71"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11116-016-9719-1"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011036"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330660"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2011.149"},{"key":"e_1_3_2_22_2","first-page":"1273","volume-title":"Artificial Intelligence and Statistics.","author":"McMahan H. B.","year":"2017","unstructured":"H. B. McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Ag\u00fcera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Artificial Intelligence and Statistics. PMLR, 1273\u20131282. Retrieved from http:\/\/proceedings.mlr.press\/v54\/mcmahan17a\/mcmahan17a.pdf"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","unstructured":"H. B. McMahan Daniel Ramage Kunal Talwar and Li Zhang. 2017b. Learning differentially private recurrent language models. arXiv:1710.06963. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.1710.06963","DOI":"10.48550\/arXiv.1710.06963"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11714"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2262376"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.33"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108441"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.11.018"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2873950"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Jinmeng Rao Song Gao Yuhao Kang and Qunying Huang. 2020. LSTM-TrajGAN: A deep learning approach to trajectory privacy protection. arXiv:2006.10521. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.2006.10521","DOI":"10.48550\/arXiv.2006.10521"},{"issue":"4","key":"e_1_3_2_31_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3510032","article-title":"GRNN: Generative regression neural network\u2014A data leakage attack for federated learning","volume":"13","author":"Ren Hanchi","year":"2022","unstructured":"Hanchi Ren, Jingjing Deng, and Xianghua Xie. 2022. GRNN: Generative regression neural network\u2014A data leakage attack for federated learning. ACM Transactions on Intelligent Systems and Technology (TIST) 13, 4 (2022), 1\u201324.","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/352871.352887"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2011.18"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2018.02.005"},{"key":"e_1_3_2_35_2","unstructured":"Jingyuan Wang Ning Wu Wayne Xin Zhao Fanzhang Peng and Xin Lin. 2019b. Empowering A* search algorithms with neural networks for personalized route recommendation. arXiv:1907.08489. Retrieved from http:\/\/arxiv.org\/abs\/1907.08489"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3068479"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.6339\/21-JDS1004"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","unstructured":"Chuhan Wu Fangzhao Wu Yang Cao Yongfeng Huang and Xing Xie. 2021. FedGNN: Federated graph neural network for privacy-preserving recommendation. arXiv:2102.04925. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.2102.04925","DOI":"10.48550\/arXiv.2102.04925"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2017.1400548"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869807"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1003919"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Bo Zhao Konda Reddy Mopuri and Hakan Bilen. 2020. iDLG: Improved deep leakage from gradients. arXiv:2001.02610. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.2001.02610","DOI":"10.48550\/arXiv.2001.02610"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3185994"},{"key":"e_1_3_2_45_2","unstructured":"Yu Zheng Hao Fu Xing Xie Wei-Ying Ma and Quannan Li. 2011. Geolife GPS trajectory dataset\u2014User Guide (geolife gps trajectories 1.1 ed.). Retrieved from https:\/\/www.microsoft.com\/en-us\/research\/publication\/geolife-gps-trajectory-dataset-user-guide\/"},{"key":"e_1_3_2_46_2","volume-title":"Proceedings of the Advances in Neural Information Processing Systems,","volume":"32","author":"Zhu Ligeng","year":"2019","unstructured":"Ligeng Zhu, Zhijian Liu, and Song Han. 2019. Deep leakage from gradients. In Proceedings of the Advances in Neural Information Processing Systems, Vol. 32."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670412","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3670412","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:38Z","timestamp":1750291538000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3670412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,26]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,2,28]]}},"alternative-id":["10.1145\/3670412"],"URL":"https:\/\/doi.org\/10.1145\/3670412","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,26]]},"assertion":[{"value":"2023-08-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}