{"title":"TRAPDROID:裸机Android恶意软件行为分析框架","authors":"Halit Alptekin, Can Yildizli, E. Savaş, A. Levi","doi":"10.23919/ICACT.2019.8702030","DOIUrl":null,"url":null,"abstract":"In the realm of mobile devices, malicious applications pose considerable threats to individuals, companies and governments. Cyber security researchers are in a constant race against malware developers and analyze their new methods to exploit them for better detection. In this paper, we present TRAPDROID, a dynamic malware analysis framework mostly focused on capturing unified behavior profiles of applications by analyzing them on physical devices in real-time. Our framework processes events, which are collected from system calls, binder communications, process stats, and hardware performance counters and combines them into a simple, yet meaningful behavior format. We evaluated our framework’s detection rate and performance by analyzing an up-to-date malware dataset, which also contains specially crafted applications with malicious intent. The framework is easy to use, fast and providing high accuracy in malware detection with relatively low overhead.","PeriodicalId":226261,"journal":{"name":"2019 21st International Conference on Advanced Communication Technology (ICACT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"TRAPDROID: Bare-Metal Android Malware Behavior Analysis Framework\",\"authors\":\"Halit Alptekin, Can Yildizli, E. Savaş, A. Levi\",\"doi\":\"10.23919/ICACT.2019.8702030\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the realm of mobile devices, malicious applications pose considerable threats to individuals, companies and governments. Cyber security researchers are in a constant race against malware developers and analyze their new methods to exploit them for better detection. In this paper, we present TRAPDROID, a dynamic malware analysis framework mostly focused on capturing unified behavior profiles of applications by analyzing them on physical devices in real-time. Our framework processes events, which are collected from system calls, binder communications, process stats, and hardware performance counters and combines them into a simple, yet meaningful behavior format. We evaluated our framework’s detection rate and performance by analyzing an up-to-date malware dataset, which also contains specially crafted applications with malicious intent. The framework is easy to use, fast and providing high accuracy in malware detection with relatively low overhead.\",\"PeriodicalId\":226261,\"journal\":{\"name\":\"2019 21st International Conference on Advanced Communication Technology (ICACT)\",\"volume\":\"18 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 21st International Conference on Advanced Communication Technology (ICACT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.23919/ICACT.2019.8702030\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 21st International Conference on Advanced Communication Technology (ICACT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.23919/ICACT.2019.8702030","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
In the realm of mobile devices, malicious applications pose considerable threats to individuals, companies and governments. Cyber security researchers are in a constant race against malware developers and analyze their new methods to exploit them for better detection. In this paper, we present TRAPDROID, a dynamic malware analysis framework mostly focused on capturing unified behavior profiles of applications by analyzing them on physical devices in real-time. Our framework processes events, which are collected from system calls, binder communications, process stats, and hardware performance counters and combines them into a simple, yet meaningful behavior format. We evaluated our framework’s detection rate and performance by analyzing an up-to-date malware dataset, which also contains specially crafted applications with malicious intent. The framework is easy to use, fast and providing high accuracy in malware detection with relatively low overhead.