The exponential growth of malware has created a significant threat in our daily lives, which heavily rely on computers running all kinds of software. Malware writers create malicious software by creating new variants, new innovations, new infections and more obfuscated malware by using techniques such as packing and encrypting techniques. Malicious software classification and detection play an important role and a big challenge for cyber security research. Due to the increasing rate of false alarm, the accurate classification and detection of malware is a big necessity issue to be solved. In this research, eight malware family have been classifying according to their family the research provides four feature selection algorithms to select best feature for multiclass classification problem. Comparing. Then find these algorithms top 100 features are selected to performance evaluations. Five machine learning algorithms is compared to find best models. Then frequency distribution of features are find by feature ranking of best model. At last it is said that frequency distribution of every character of API call sequence can be used to classify malware family.
","abstract_html":"<p>The exponential growth of malware has created a significant threat in our daily lives, which heavily rely on computers running all kinds of software. Malware writers create malicious software by creating new variants, new innovations, new infections and more obfuscated malware by using techniques such as packing and encrypting techniques. Malicious software classification and detection play an important role and a big challenge for cyber security research. Due to the increasing rate of false alarm, the accurate classification and detection of malware is a big necessity issue to be solved. In this research, eight malware family have been classifying according to their family the research provides four feature selection algorithms to select best feature for multiclass classification problem. Comparing. Then find these algorithms top 100 features are selected to performance evaluations. Five machine learning algorithms is compared to find best models. Then frequency distribution of features are find by feature ranking of best model. At last it is said that frequency distribution of every character of API call sequence can be used to classify malware family.</p>","abstract_has_math":false,"creators":["Asrafi, Nusrat"],"institution":null,"degree_name":"Master of Science in Computer Science (MSCS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Dr. Dan Chia-Tien Lo","Dr. Coskun Cetinkaya","Dr. Donghyun Kim"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-04-28T07:00:00Z","date_published":"2020-04-28T07:00:00Z","updated_at":"2026-07-24T02:43:42Z","subjects":["Frequency Distribution of features for Malware family classification/","Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.kennesaw.edu/cs_etd/44","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Dr. Dan Chia-Tien Lo","Dr. Coskun Cetinkaya","Dr. Donghyun Kim"]},{"key":"dc:creator","label":"Author","values":["Asrafi, Nusrat"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2021-05-07T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Computer Science (MSCS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Frequency Distribution of features for Malware family classification/","Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.kennesaw.edu/cs_etd/44"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The exponential growth of malware has created a significant threat in our daily lives, which heavily rely on computers running all kinds of software. Malware writers create malicious software by creating new variants, new innovations, new infections and more obfuscated malware by using techniques such as packing and encrypting techniques. Malicious software classification and detection play an important role and a big challenge for cyber security research. Due to the increasing rate of false alarm, the accurate classification and detection of malware is a big necessity issue to be solved. In this research, eight malware family have been classifying according to their family the research provides four feature selection algorithms to select best feature for multiclass classification problem. Comparing. Then find these algorithms top 100 features are selected to performance evaluations. Five machine learning algorithms is compared to find best models. Then frequency distribution of features are find by feature ranking of best model. At last it is said that frequency distribution of every character of API call sequence can be used to classify malware family.
"]},{"key":"dc:title","label":"Title","values":["Performance of Malware Classification on Machine Learning using Feature Selection"]}]}],"canonical_facts":{"dc:contributor":["Dr. Dan Chia-Tien Lo","Dr. Coskun Cetinkaya","Dr. Donghyun Kim"],"dc:creator":["Asrafi, Nusrat"],"dc:date.available":["2021-05-07T07:00:00Z"],"dc:description.abstract":["The exponential growth of malware has created a significant threat in our daily lives, which heavily rely on computers running all kinds of software. Malware writers create malicious software by creating new variants, new innovations, new infections and more obfuscated malware by using techniques such as packing and encrypting techniques. Malicious software classification and detection play an important role and a big challenge for cyber security research. Due to the increasing rate of false alarm, the accurate classification and detection of malware is a big necessity issue to be solved. In this research, eight malware family have been classifying according to their family the research provides four feature selection algorithms to select best feature for multiclass classification problem. Comparing. Then find these algorithms top 100 features are selected to performance evaluations. Five machine learning algorithms is compared to find best models. Then frequency distribution of features are find by feature ranking of best model. At last it is said that frequency distribution of every character of API call sequence can be used to classify malware family.
"],"dc:identifier":["https://digitalcommons.kennesaw.edu/cs_etd/44"],"dc:subject":["Frequency Distribution of features for Malware family classification/","Computer Engineering"],"dc:title":["Performance of Malware Classification on Machine Learning using Feature Selection"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science in Computer Science (MSCS)"]},"updated_at":"2026-07-24T02:43:42Z"}