{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/throttling-malware-families-in-2d","title":"Throttling Malware Families in 2D","arxiv_id":"1901.10590","date":"2019-01-29","proceeding":null,"authors":["Mohamed Nassar","Haidar Safa"],"abstract":"Malicious software are categorized into families based on their static and\ndynamic characteristics, infection methods, and nature of threat. Visual\nexploration of malware instances and families in a low dimensional space helps\nin giving a first overview about dependencies and relationships among these\ninstances, detecting their groups and isolating outliers. Furthermore, visual\nexploration of different sets of features is useful in assessing the quality of\nthese sets to carry a valid abstract representation, which can be later used in\nclassification and clustering algorithms to achieve a high accuracy. In this\npaper, we investigate one of the best dimensionality reduction techniques known\nas t-SNE to reduce the malware representation from a high dimensional space\nconsisting of thousands of features to a low dimensional space. We experiment\nwith different feature sets and depict malware clusters in 2-D. Surprisingly,\nt-SNE does not only provide nice 2-D drawings, but also dramatically increases\nthe generalization power of SVM classifiers. Moreover, obtained results showed\nthat cross-validation accuracy is much better using the 2-D embedded\nrepresentation of samples than using the original high-dimensional\nrepresentation.","url_abs":"http://arxiv.org/abs/1901.10590v1","url_pdf":"http://arxiv.org/pdf/1901.10590v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"throttling-malware-families-in-2d","repo_url":"https://github.com/mnassar/malware-viz","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"affine-coupling","method_name":"Affine Coupling"},{"method_slug":"normalizing-flows","method_name":"Normalizing Flows"},{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}