{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T03:17:36Z","timestamp":1783826256288,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T00:00:00Z","timestamp":1712880000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Luxembourg National Research Fund (FNR)","award":["C21\/IS\/16344458"],"award-info":[{"award-number":["C21\/IS\/16344458"]}]},{"name":"Luxembourg National Research Fund (FNR)","award":["NCER22\/IS\/16570468\/NCERFT"],"award-info":[{"award-number":["NCER22\/IS\/16570468\/NCERFT"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,12]]},"DOI":"10.1145\/3597503.3639094","type":"proceedings-article","created":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T16:43:26Z","timestamp":1712940206000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Revisiting Android App Categorization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5963-4599","authenticated-orcid":false,"given":"Marco","family":"Alecci","sequence":"first","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6052-6184","authenticated-orcid":false,"given":"Jordan","family":"Samhi","sequence":"additional","affiliation":[{"name":"CISPA Helmholtz Center for Information Security, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7270-9869","authenticated-orcid":false,"given":"Tegawende F.","family":"Bissyande","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4052-475X","authenticated-orcid":false,"given":"Jacques","family":"Klein","sequence":"additional","affiliation":[{"name":"University of Luxembourg, Luxembourg, Luxembourg"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"2024 IEEE\/ACM 21st International Conference on Mining Software Repositories (MSR). IEEE Computer Society.","author":"Alecci Marco","year":"2024","unstructured":"Marco Alecci, Pedro J. R. Jim\u00e9nez, Kevin Allix, Tegawend\u00e9 F. Bissyand\u00e9, and Jacques Klein. 2024. AndroZoo: A Retrospective with a Glimpse into the Future. In 2024 IEEE\/ACM 21st International Conference on Mining Software Repositories (MSR). IEEE Computer Society."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2901739.2903508"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-019-09726-5"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Afnan Alsubaihin Federica Sarro Sue Black L. Capra Mark Harman Yue Jia and Y. Zhang. 2016. Clustering Mobile Apps Based on Mined Textual Features. 1--10. 10.1145\/2961111.2962600","DOI":"10.1145\/2961111.2962600"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-008-9066-8"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-8471-3_12"},{"key":"e_1_3_2_1_7_1","volume-title":"DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket. In Network and Distributed System Security Symposium.","author":"Arp Dan","year":"2014","unstructured":"Dan Arp, Michael Spreitzenbarth, Malte Hubner, Hugo Gascon, and Konrad Rieck. 2014. DREBIN: Effective and Explainable Detection of Android Malware in Your Pocket. In Network and Distributed System Security Symposium."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE-C.2017.130"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2018.01.003"},{"key":"e_1_3_2_1_11_1","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel M. Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. arXiv:2005.14165 [cs.CL]"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/03610927408827101"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2685305"},{"key":"e_1_3_2_1_14_1","volume-title":"Kevin Allix, Tegawend\u00e9 F. Bissyand\u00e9, and Jacques Klein.","author":"Daoudi Nadia","year":"2021","unstructured":"Nadia Daoudi, Jordan Samhi, Abdoul Kader Kabore, Kevin Allix, Tegawend\u00e9 F. Bissyand\u00e9, and Jacques Klein. 2021. DexRay: A Simple, yet Effective Deep Learning Approach to Android Malware Detection Based on Image Representation of Bytecode. In Deployable Machine Learning for Security Defense, Gang Wang, Arridhana Ciptadi, and Ali Ahmadzadeh (Eds.). Springer International Publishing, Cham, 81--106."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.1979.4766909"},{"key":"e_1_3_2_1_16_1","unstructured":"Anthony Desnos. 2011. https:\/\/github.com\/androguard\/androguard."},{"key":"e_1_3_2_1_17_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805 [cs.CL]","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. arXiv:1810.04805 [cs.CL]"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474827"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2948212"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1983.10478008"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1136800"},{"key":"e_1_3_2_1_22_1","volume-title":"Checking App Behavior Against App Descriptions. In ICSE '14: Proceedings of the 2014 International Conference on Software Engineering","author":"Gorla Alessandra","year":"2014","unstructured":"Alessandra Gorla, Ilaria Tavecchia, Florian Gross, and Andreas Zeller. 2014. Checking App Behavior Against App Descriptions. In ICSE '14: Proceedings of the 2014 International Conference on Software Engineering (Hyderabad, India). ACM Press, 292--302."},{"key":"e_1_3_2_1_23_1","volume-title":"Luigi Lo Iacono, and Jan Tolsdorf","author":"Gruschka Nils","year":"2018","unstructured":"Nils Gruschka, Luigi Lo Iacono, and Jan Tolsdorf. 2018. Classification of Android App Permissions."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908075"},{"key":"e_1_3_2_1_25_1","unstructured":"IEEEXplore. 2023. https:\/\/ieeexplore.ieee.org\/Xplore\/home.jsp."},{"key":"e_1_3_2_1_26_1","first-page":"20150202","article-title":"Principal component analysis: a review and recent developments. Philosophical transactions of the royal society A","volume":"374","author":"Jolliffe Ian T","year":"2016","unstructured":"Ian T Jolliffe and Jorge Cadima. 2016. Principal component analysis: a review and recent developments. Philosophical transactions of the royal society A: Mathematical, Physical and Engineering Sciences 374, 2065 (2016), 20150202.","journal-title":"Mathematical, Physical and Engineering Sciences"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993259.2993265"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2020.3026335"},{"key":"e_1_3_2_1_29_1","unstructured":"ACM Digital Library. 2023. https:\/\/dl.acm.org\/."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-020-01238-9"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2630689"},{"key":"e_1_3_2_1_33_1","volume-title":"Weinberger (Eds.)","volume":"26","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In Advances in Neural Information Processing Systems, C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger (Eds.), Vol. 26. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013\/file\/9aa42b31882ec039965f3c4923ce901b-Paper.pdf"},{"key":"e_1_3_2_1_34_1","volume-title":"Data Science: From Research to Application","author":"Ebrahimi A. Mohammad","unstructured":"A. Mohammad Ebrahimi, M. Saber Gholami, Saeedeh Momtazi, M. R. Meybodi, and A. Abdollahzadeh Barforoush. 2020. Correlation Analysis of Applications' Features: A Case Study on Google Play. In Data Science: From Research to Application, Mahdi Bohlouli, Bahram Sadeghi Bigham, Zahra Narimani, Mahdi Vasighi, and Ebrahim Ansari (Eds.). Springer International Publishing, Cham, 202--216."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00051"},{"key":"e_1_3_2_1_36_1","unstructured":"Arvind Neelakantan Tao Xu Raul Puri Alec Radford Jesse Michael Han Jerry Tworek Qiming Yuan Nikolas Tezak Jong Wook Kim Chris Hallacy Johannes Heidecke Pranav Shyam Boris Power Tyna Eloundou Nekoul Girish Sastry Gretchen Krueger David Schnurr Felipe Petroski Such Kenny Hsu Madeleine Thompson Tabarak Khan Toki Sherbakov Joanne Jang Peter Welinder and Lilian Weng. 2022. Text and Code Embeddings by Contrastive Pre-Training. arXiv:2201.10005 [cs.CL]"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966078"},{"key":"e_1_3_2_1_38_1","unstructured":"Babatunde Olabenjo. 2016. Applying Naive Bayes Classification to Google Play Apps Categorization. arXiv:1608.08574 [cs.LG]"},{"key":"e_1_3_2_1_39_1","unstructured":"OpenAI. 2022. https:\/\/openai.com\/blog\/introducing-text-and-code-embeddings."},{"key":"e_1_3_2_1_41_1","unstructured":"OpenAI. 2023. https:\/\/github.com\/openai\/openai-cookbook\/blob\/main\/examples\/How_to_count_tokens_with_tiktoken.ipynb."},{"key":"e_1_3_2_1_42_1","unstructured":"OpenAI. 2023. https:\/\/openai.com\/blog\/new-and-improved-embedding-model."},{"key":"e_1_3_2_1_43_1","unstructured":"OpenAI. 2023. https:\/\/platform.openai.com\/docs\/guides\/embeddings."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313427"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1971.10482356"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2020.00032"},{"key":"e_1_3_2_1_50_1","unstructured":"Google Scholar. 2023. https:\/\/scholar.google.com\/."},{"key":"e_1_3_2_1_51_1","unstructured":"Sevil Sen and Burcu Can. 2021. Android Security using NLP Techniques: A Review. arXiv:2107.03072 [cs.CR]"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC52881.2021.00050"},{"key":"e_1_3_2_1_53_1","unstructured":"Tiezhu Sun Weiguo Pian Nadia Daoudi Kevin Allix Tegawend\u00e9 F. Bissyand\u00e9 and Jacques Klein. 2023. LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning. arXiv:2308.01413 [cs.CL]"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC51575.2020.9344944"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2686851"},{"key":"e_1_3_2_1_56_1","unstructured":"Virus Total. 2020. Virus total free online virus malware and url scanner. https:\/\/www.virustotal.com\/en"},{"key":"e_1_3_2_1_57_1","unstructured":"Saarland University. 2014. https:\/\/www.st.cs.uni-saarland.de\/appmining\/."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.01.019"},{"key":"e_1_3_2_1_59_1","unstructured":"Ryszard Wi\u015bniewski. 2016. https:\/\/ibotpeaches.github.io\/Apktool\/."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2017.04.007"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","unstructured":"Chengpeng Zhang Haoyu Wang Ran Wang Yao Guo and Guoai Xu. 2018. Rechecking App Behavior against App Description in the Context of Third-party Libraries. 665--710. 10.18293\/SEKE2018-180","DOI":"10.18293\/SEKE2018-180"}],"event":{"name":"ICSE '24: IEEE\/ACM 46th International Conference on Software Engineering","location":"Lisbon Portugal","acronym":"ICSE '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering","IEEE CS","Faculty of Engineering of University of Porto"]},"container-title":["Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639094","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3597503.3639094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:49:11Z","timestamp":1750286951000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3597503.3639094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,12]]},"references-count":60,"alternative-id":["10.1145\/3597503.3639094","10.1145\/3597503"],"URL":"https:\/\/doi.org\/10.1145\/3597503.3639094","relation":{},"subject":[],"published":{"date-parts":[[2024,4,12]]},"assertion":[{"value":"2024-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}