{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:21:23Z","timestamp":1767705683013,"version":"3.41.0"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001602","name":"Science Foundation Ireland","doi-asserted-by":"crossref","award":["16\/IA\/4610"],"award-info":[{"award-number":["16\/IA\/4610"]}],"id":[{"id":"10.13039\/501100001602","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Recomm. Syst."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>In practice, users of a Recommender System (RS) fall into a few clusters based on their preferences. In this work, we conduct a systematic study on user-cluster targeted data poisoning attacks on Matrix Factorisation (MF)-based RS, where an adversary injects fake users with falsely crafted user-item feedback to promote an item to a specific user cluster. We analyze how user and item feature matrices change after data poisoning attacks and identify the factors that influence the effectiveness of the attack on these feature matrices. We demonstrate that the adversary can easily target specific user clusters with minimal effort and that some items are more susceptible to attacks than others. Our theoretical analysis has been validated by the experimental results obtained from two real-world datasets. Our observations from the study could serve as a motivating point to design a more robust RS.<\/jats:p>","DOI":"10.1145\/3674157","type":"journal-article","created":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T11:17:04Z","timestamp":1718968624000},"page":"1-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluating Impact of User-Cluster Targeted Attacks in Matrix Factorisation Recommenders"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9290-3946","authenticated-orcid":false,"given":"Sulthana","family":"Shams","sequence":"first","affiliation":[{"name":"School of Computer Science and Statistics, Trinity College Dublin, Dublin 2, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4056-4014","authenticated-orcid":false,"given":"Douglas","family":"Leith","sequence":"additional","affiliation":[{"name":"School of Computer Science and Statistics, Trinity College Dublin, Dublin 2, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"e_1_3_3_2_2","volume-title":"ProPublica","author":"Angwin Julia","year":"2016","unstructured":"Julia Angwin and Terry Parris Jr.2016. Facebook lets advertisers exclude users by race. In ProPublica. Retrieved from https:\/www.propublica.org\/inproceedings\/facebook-lets-advertisers-exclude-users-by-race"},{"key":"e_1_3_3_3_2","volume-title":"Google AdsR","author":"Bindra Chetna","year":"2021","unstructured":"Chetna Bindra. 2021. Building a privacy-first future for web advertising. In Google Ads. Retrieved from https:\/\/blog.google\/products\/ads-commerce\/2021-01-privacy-sandbox\/"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3041760"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298689.3347031"},{"key":"e_1_3_3_6_2","volume-title":"arXiv preprint arXiv:1408.6491","author":"Datta Amit","year":"2014","unstructured":"Amit Datta, Michael Carl Tschantz, and Anupam Datta. 2014. Automated experiments on ad privacy settings: A tale of opacity, choice, and discrimination. arXiv preprint arXiv:1408.6491."},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371877"},{"key":"e_1_3_3_8_2","article-title":"How merchants use Facebook to flood Amazon with fake reviews","author":"Dwoskin Elizabeth","year":"2018","unstructured":"Elizabeth Dwoskin and Craig Timberg. 2018. How merchants use Facebook to flood Amazon with fake reviews. In Washington Post.Retrieved from https:\/\/www.washingtonpost.com\/business\/economy\/how-merchants-secretly-use-facebook-to-flood-amazon-with-fake-reviews\/2018\/04\/23\/5dad1e30-4392-11e8-8569-26fda6b404c7-story.html","journal-title":"R"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467180"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380072"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3274694.3274706"},{"key":"e_1_3_3_12_2","volume-title":"Netflix NewsR","author":"Gomez-Uribe Carlos","year":"2016","unstructured":"Carlos Gomez-Uribe. 2016. A global approach to recommendations. In Netflix News. Retrieved from https:\/\/about.netflix.com\/en\/news\/a-global-approach-to-recommendations"},{"key":"e_1_3_3_13_2","volume-title":"The Washington PostR","author":"Guarino Ben","year":"2018","unstructured":"Ben Guarino. 2018. Anti vaccine reviewers target children\u2019s books on Amazon. In The Washington Post. Retrieved from https:\/\/www.washingtonpost.com\/news\/speaking-of-science\/wp\/2018\/04\/09\/anti-vaccine-reviewers-target-childrens-books-on-amazon\/"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3465456.3467589"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Thomas Hofmann. 2004. Latent semantic models for collaborative filtering. ACM Trans. Inf. Syst. 22 1) (2004) 89\u2013115. DOI:10.1145\/963770.963774","DOI":"10.1145\/963770.963774"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013539"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24525"},{"key":"e_1_3_3_19_2","volume-title":"Amazon Web Services (AWS)R","author":"Katidis Pavlos Ioannou","year":"2022","unstructured":"Pavlos Ioannou Katidis and Christian Bonzelet. 2022. Use machine learning to target your customers based on their interest in a product or product attribute. In Amazon Web Services (AWS). Retrieved from https:\/\/aws.amazon.com\/blogs\/messaging-and-targeting\/use-machine-learning-to-target-your-customers-based-on-their-interest-in-a-product-or-product-attribute"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/988672.988726"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157308"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411884"},{"volume-title":"Meta AdsR","year":"2023","key":"e_1_3_3_24_2","unstructured":"Meta. 2023. Ad targeting: How to find people most likely to respond to your ad. In Meta Ads. Retrieved from https:\/\/www.facebook.com\/business\/ads\/ad-targeting"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-018-9655-x"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICETET.2010.121"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/1278366.1278372"},{"key":"e_1_3_3_28_2","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1007\/11891321_6","volume-title":"Proceedings of the 7th International Conference on Knowledge Discovery on the Web: Advances in Web Mining and Web Usage Analysis (WebKDD\u201905)","volume":"4198","author":"Mobasher Bamshad","year":"2005","unstructured":"Bamshad Mobasher, Robin Burke, Chad Williams, and Runa Bhaumik. 2005. Analysis and detection of segment-focused attacks against collaborative recommendation. In Proceedings of the 7th International Conference on Knowledge Discovery on the Web: Advances in Web Mining and Web Usage Analysis (WebKDD\u201905), Vol. 4198. 96\u2013118."},{"key":"e_1_3_3_29_2","first-page":"377","volume-title":"Proceedings of the 1st International Conference on Information and Communication Technology for Intelligent Systems","author":"Patel Krupa","year":"2015","unstructured":"Krupa Patel, Amit Thakkar, Chandni Shah, and Kamlesh Makvana. 2015. A state of art survey on shilling attack in collaborative filtering based recommendation system. In Proceedings of the 1st International Conference on Information and Communication Technology for Intelligent Systems. Springer, 377\u2013385."},{"key":"e_1_3_3_30_2","volume-title":"Google Research and Ads","author":"Ravichandran Deepak","year":"2009","unstructured":"Deepak Ravichandran and Sergei Vassilvitskii. 2009. Evaluation of cohort algorithms for the FLoC API. In Google Research and Ads. Retrieved from DOI:https:\/\/github.com\/google\/ads-privacy\/blob\/master\/proposals\/FLoC\/FLOC-Whitepaper-Google.pdf"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412488"},{"key":"e_1_3_3_32_2","volume-title":"QuartzR","author":"Rodriguez Ashley","year":"2017","unstructured":"Ashley Rodriguez. 2017. Netflix divides its 93 million users around the world into 1,300 \u201ctaste communities.\u201d In Quartz. Retrieved from https:\/\/qz.com\/939195\/netflix-nflx-divides-its-93-million-users-around-the-world-not-by-geography-but-into-1300-taste-communities"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463033"},{"key":"e_1_3_3_34_2","unstructured":"Sulthana Shams and Douglas Leith. 2023. Attack Detection Using Item Vector Shift in Matrix Factorisation Recommenders. arxiv:cs.IR\/2312.00512"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/Cyber-RCI55324.2022.10032671"},{"key":"e_1_3_3_36_2","volume-title":"The New York TimesR","author":"Simonetti Isabella","year":"2022","unstructured":"Isabella Simonetti. 2022. Amazon fake reviews lawsuit. In The New York Times. Retrieved from https:\/\/www.nytimes.com\/2022\/07\/19\/business\/amazon-fake-reviews-lawsuit.html?smid=url-share"},{"key":"e_1_3_3_37_2","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Ungar Lyle H.","year":"1998","unstructured":"Lyle H. Ungar and Dean Phillips Foster. 1998. Clustering methods for collaborative filtering. In Proceedings of the AAAI Conference on Artificial Intelligence. Retrieved from DOI:https:\/\/api.semanticscholar.org\/CorpusID:6565845"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462914"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/500737.500768"},{"key":"e_1_3_3_40_2","first-page":"553","volume-title":"Proceedings of the European Conference on Artificial Intelligence (ECAI\u201920)","author":"Xu Yangjun","year":"2020","unstructured":"Yangjun Xu, Liang Chen, Fenfang Xie, Weibo Hu, Jieming Zhu, Chuan Chen, and Zibin Zheng. 2020. Directional adversarial training for recommender systems. In Proceedings of the European Conference on Artificial Intelligence (ECAI\u201920). 553\u2013560."},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076056"},{"key":"e_1_3_3_42_2","first-page":"3203","volume-title":"Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI\u201917)","author":"Xue Hong-Jian","year":"2017","unstructured":"Hong-Jian Xue, Xin-Yu Dai, Jianbing Zhang, Shujian Huang, and Jiajun Chen. 2017. Deep matrix factorization models for recommender systems. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI\u201917). AAAI Press, 3203\u20133209."},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISDEA.2012.381"}],"container-title":["ACM Transactions on Recommender Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674157","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:26Z","timestamp":1750291046000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674157"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"references-count":42,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3674157"],"URL":"https:\/\/doi.org\/10.1145\/3674157","relation":{},"ISSN":["2770-6699"],"issn-type":[{"type":"electronic","value":"2770-6699"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"2023-02-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}