{"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/towards-building-an-intelligent-anti-malware","title":"Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine (SVM) for Malware Classification","arxiv_id":"1801.00318","date":"2017-12-31","proceeding":null,"authors":["Abien Fred Agarap"],"abstract":"Effective and efficient mitigation of malware is a long-time endeavor in the\ninformation security community. The development of an anti-malware system that\ncan counteract an unknown malware is a prolific activity that may benefit\nseveral sectors. We envision an intelligent anti-malware system that utilizes\nthe power of deep learning (DL) models. Using such models would enable the\ndetection of newly-released malware through mathematical generalization. That\nis, finding the relationship between a given malware $x$ and its corresponding\nmalware family $y$, $f: x \\mapsto y$. To accomplish this feat, we used the\nMalimg dataset (Nataraj et al., 2011) which consists of malware images that\nwere processed from malware binaries, and then we trained the following DL\nmodels 1 to classify each malware family: CNN-SVM (Tang, 2013), GRU-SVM\n(Agarap, 2017), and MLP-SVM. Empirical evidence has shown that the GRU-SVM\nstands out among the DL models with a predictive accuracy of ~84.92%. This\nstands to reason for the mentioned model had the relatively most sophisticated\narchitecture design among the presented models. The exploration of an even more\noptimal DL-SVM model is the next stage towards the engineering of an\nintelligent anti-malware system.","url_abs":"http://arxiv.org/abs/1801.00318v2","url_pdf":"http://arxiv.org/pdf/1801.00318v2.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":"towards-building-an-intelligent-anti-malware","repo_url":"https://github.com/AFAgarap/malware-classification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"malware-classification","task_name":"Malware Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/malware-classification-on-malimg-dataset","task":"Malware Classification","dataset":"Malimg Dataset","model":"GRU + SVM","rank_in_archive_order":3,"of":5,"metrics":{"Accuracy":"0.8492"},"uses_additional_data":false},{"leaderboard":"/sota/malware-classification-on-malimg-dataset","task":"Malware Classification","dataset":"Malimg Dataset","model":"FFNN + SVM","rank_in_archive_order":4,"of":5,"metrics":{"Accuracy":"0.8047"},"uses_additional_data":false},{"leaderboard":"/sota/malware-classification-on-malimg-dataset","task":"Malware Classification","dataset":"Malimg Dataset","model":"CNN + SVM","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy":"0.7723"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}