{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:40:35Z","timestamp":1760488835180,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,27]]},"DOI":"10.1145\/3704268.3748684","type":"proceedings-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T16:44:47Z","timestamp":1756313087000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Clustering of the SOREL Malware Corpus"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6950-5912","authenticated-orcid":false,"given":"Raguvir","family":"S","sequence":"first","affiliation":[{"name":"Department of Computer Science and Electrical, Engineering, UMBC, Baltimore, MD, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9494-7139","authenticated-orcid":false,"given":"Charles","family":"Nicholas","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Electrical, Engineering, UMBC, Baltimore, MD, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,8,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2963724"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/829502.830043"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ARES.2015.57"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSEC.2023.3236543"},{"key":"e_1_3_2_1_5_1","volume-title":"Superminhash-A new minwise hashing algorithm for jaccard similarity estimation. arXiv preprint arXiv:1706.05698","author":"Ertl Otmar","year":"2017","unstructured":"Otmar Ertl. 2017. Superminhash-A new minwise hashing algorithm for jaccard similarity estimation. arXiv preprint arXiv:1706.05698 (2017)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/2449288.2449314"},{"key":"e_1_3_2_1_7_1","volume-title":"DIMVA 2012","author":"Hanna Steve","year":"2013","unstructured":"Steve Hanna, Ling Huang, Edward Wu, Saung Li, Charles Chen, and Dawn Song. 2013. Juxtapp: A scalable system for detecting code reuse among android applications. In Detection of Intrusions and Malware, and Vulnerability Assessment: 9th International Conference, DIMVA 2012, Heraklion, Crete, Greece, July 26-27, 2012, Revised Selected Papers 9. Springer, 62--81."},{"key":"e_1_3_2_1_8_1","volume-title":"Rudd","author":"Harang Richard E.","year":"2020","unstructured":"Richard E. Harang and Ethan M. Rudd. 2020. SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection. https:\/\/arxiv.org\/abs\/2012.07634.arXiv:2012.07634"},{"key":"e_1_3_2_1_9_1","volume-title":"2013 USENIX Annual Technical Conference (USENIX ATC 13)","author":"Hu Xin","year":"2013","unstructured":"Xin Hu, Kang G Shin, Sandeep Bhatkar, and Kent Griffin. 2013. {MutantX-S}: Scalable Malware Clustering Based on Static Features. In 2013 USENIX Annual Technical Conference (USENIX ATC 13). 187--198."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2014.6883436"},{"key":"e_1_3_2_1_11_1","volume-title":"N-gram opcode analysis for android malware detection. arXiv preprint arXiv:1612.01445","author":"Kang BooJoong","year":"2016","unstructured":"BooJoong Kang, Suleiman Y Yerima, Sakir Sezer, and Kieran McLaughlin. 2016. N-gram opcode analysis for android malware detection. arXiv preprint arXiv:1612.01445 (2016)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0046-3"},{"key":"e_1_3_2_1_13_1","volume-title":"2019 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 178--183","author":"Lee Shinho","year":"2019","unstructured":"Shinho Lee, Wookhyun Jung, Sangwon Kim, and Eui Tak Kim. 2019. Android malware similarity clustering using method based opcode sequence and jac-card index. In 2019 International Conference on Information and Communication Technology Convergence (ICTC). IEEE, 178--183."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2007.48"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3468264.3473925"},{"key":"e_1_3_2_1_16_1","volume-title":"Modern hierarchical, agglomerative clustering algorithms. arXiv preprint arXiv:1109.2378","author":"M\u00fcllner Daniel","year":"2011","unstructured":"Daniel M\u00fcllner. 2011. Modern hierarchical, agglomerative clustering algorithms. arXiv preprint arXiv:1109.2378 (2011)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCS.2015.27"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-008-0150-6"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41237-018-0075-7"},{"key":"e_1_3_2_1_20_1","unstructured":"VirusTotal. [n. d.]. File statistics during last 7 days. https:\/\/www.virustotal.com\/en\/statistics\/ Last accessed on 2025-06-13."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/17.9.763"}],"event":{"name":"DocEng '25: ACM Symposium on Document Engineering 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Nottingham United Kingdom","acronym":"DocEng '25"},"container-title":["Proceedings of the 2025 ACM Symposium on Document Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704268.3748684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T18:26:24Z","timestamp":1760466384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704268.3748684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,27]]},"references-count":21,"alternative-id":["10.1145\/3704268.3748684","10.1145\/3704268"],"URL":"https:\/\/doi.org\/10.1145\/3704268.3748684","relation":{},"subject":[],"published":{"date-parts":[[2025,8,27]]},"assertion":[{"value":"2025-08-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}