Ad Hoc Networks 101 (2020) 102098
Contents lists available at ScienceDirect
Ad Hoc Networks
journal homepage: www.elsevier.com/locate/adhoc
End-to-end malware detection for android IoT devices using deep learning
Zhongru Ren a, Haomin Wu d, Qian Ningc, Iftikhar Hussain e, Bingcai Chen a,b,lowast;
a School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China
b School of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China c College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China d Electronic Information Engineering Department of Wuhan Polytechnic, Wuhan 430074, China
e School of Computer Science and Technology, University of Science and Technology of China, Hefei 230000, China
a r t i c l e i n f o a b s t r a c t
Article history:
Received 1 December 2019
Revised 5 February 2020
Accepted 12 February 2020
Available online 14 February 2020
Keywords:
Android malware detection IoT
End-to-end Deep learning
The Internet of Things (IoT) has grown rapidly in recent years and has become one of the most active areas in the global market. As an open source platform with a large number of users, Android has become the driving force behind the rapid development of the IoT, also attracted malware attacks. Considering the explosive growth of Android malware in recent years, there is an urgent need to propose efficient methods for Android malware detection. Although the existing Android malware detection methods based on machine learning has achieved encouraging performance, most of these methods require a lot of time and effort from the malware analysts to build dynamic or static features, so these methods are difficult to apply in practice. Therefore, end-to-end malware detection methods without human expert intervention are required. This paper proposes two end-to-end Android malware detection methods based on deep learning. Compared with the existing detection methods, the proposed methods have the advantage of their end-to-end learning process. Our proposed methods resample the raw bytecodes of the classes.dex files of Android applications as input to deep learning models. These models are trained and evaluated in a dataset containing 8K benign applications and 8K malicious applications. Experiments show that the proposed methods can achieve 93.4% and 95.8% detection accuracy respectively. Compared with the existing methods, our proposed methods are not limited by input filesize, no manual feature engineering, low resource consumption, so they are more suitable for application on Android IoT devices.
copy; 2020 Elsevier B.V. All rights reserved.
Introduction
Internet of Things (IoT) has developed rapidly in recent years, and its widespread use in many fields, such as industrial control, vehicle IoT, smart home, and healthcare has made the importance of IoT security even more prominent. According to reports [1], IoT devices have become a key entry point for targeted attacks. Although routers and webcams currently account for 90% of in- fected devices, almost every IoT device is vulnerable. In particular, Android-based IoT devices have become one of the major targets of malware attacks due to the openness and universality of the An- droid platform, as shown in Fig 1. Malicious behaviors, including privacy theft, malicious deduction, traffic consumption, and remote control, seriously threaten the security and privacy of infected de- vices. According to statistics [2], the total number of Android mal-
lowast; Corresponding author.
E-mail address: china@dlut.edu.cn (B. Chen).
ware detected worldwide in 2018 reached to 26.61 million, and the monthly increase of malware reached to 520,000. In particular, a large number of Android malware uses various techniques, such as obfuscation and encryption, to evade detection, making malware detection more difficult [3]. The rapid expansion of Android mal- ware has become a huge barrier for malware analysts. Therefore, researching efficient Android malware detection methods has be- come a hot issue.
Anti-virus software companies, such as Kaspersky, McAfee, TrendMicro, and Comodo have also released their software to pro- tect against Android malware. However, studies have shown that the performance of these anti-virus software is not satisfactory, especially for malware with code obfuscation and encryption [4]. Android malware detection also has a large number of significant achievements in academia. In general, the existing methods for Android m
剩余内容已隐藏，支付完成后下载完整资料
Ad Hoc Networks 101 (2020) 102098
Contents lists available at ScienceDirect
Ad Hoc Networks
journal homepage: www.elsevier.com/locate/adhoc
End-to-end malware detection for android IoT devices using deep learning
Zhongru Ren a, Haomin Wu d, Qian Ningc, Iftikhar Hussain e, Bingcai Chen a,b,lowast;
a School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China
b School of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054, China c College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China d Electronic Information Engineering Department of Wuhan Polytechnic, Wuhan 430074, China
e School of Computer Science and Technology, University of Science and Technology of China, Hefei 230000, China
a r t i c l e i n f o a b s t r a c t
Article history:
Received 1 December 2019
Revised 5 February 2020
Accepted 12 February 2020
Available online 14 February 2020
Keywords:
Android malware detection IoT
End-to-end Deep learning
The Internet of Things (IoT) has grown rapidly in recent years and has become one of the most active areas in the global market. As an open source platform with a large number of users, Android has become the driving force behind the rapid development of the IoT, also attracted malware attacks. Considering the explosive growth of Android malware in recent years, there is an urgent need to propose efficient methods for Android malware detection. Although the existing Android malware detection methods based on machine learning has achieved encouraging performance, most of these methods require a lot of time and effort from the malware analysts to build dynamic or static features, so these methods are difficult to apply in practice. Therefore, end-to-end malware detection methods without human expert intervention are required. This paper proposes two end-to-end Android malware detection methods based on deep learning. Compared with the existing detection methods, the proposed methods have the advantage of their end-to-end learning process. Our proposed methods resample the raw bytecodes of the classes.dex files of Android applications as input to deep learning models. These models are trained and evaluated in a dataset containing 8K benign applications and 8K malicious applications. Experiments show that the proposed methods can achieve 93.4% and 95.8% detection accuracy respectively. Compared with the existing methods, our proposed methods are not limited by input filesize, no manual feature engineering, low resource consumption, so they are more suitable for application on Android IoT devices.
copy; 2020 Elsevier B.V. All rights reserved.
Introduction
Internet of Things (IoT) has developed rapidly in recent years, and its widespread use in many fields, such as industrial control, vehicle IoT, smart home, and healthcare has made the importance of IoT security even more prominent. According to reports [1], IoT devices have become a key entry point for targeted attacks. Although routers and webcams currently account for 90% of in- fected devices, almost every IoT device is vulnerable. In particular, Android-based IoT devices have become one of the major targets of malware attacks due to the openness and universality of the An- droid platform, as shown in Fig 1. Malicious behaviors, including privacy theft, malicious deduction, traffic consumption, and remote control, seriously threaten the security and privacy of infected de- vices. According to statistics [2], the total number of Android mal-
lowast; Corresponding author.
E-mail address: china@dlut.edu.cn (B. Chen).
ware detected worldwide in 2018 reached to 26.61 million, and the monthly increase of malware reached to 520,000. In particular, a large number of Android malware uses various techniques, such as obfuscation and encryption, to evade detection, making malware detection more difficult [3]. The rapid expansion of Android mal- ware has become a huge barrier for malware analysts. Therefore, researching efficient Android malware detection methods has be- come a hot issue.
Anti-virus software companies, such as Kaspersky, McAfee, TrendMicro, and Comodo have also released their software to pro- tect against Android malware. However, studies have shown that the performance of these anti-virus software is not satisfactory, especially for malware with code obfuscation and encryption [4]. Android malware detection also has a large number of significant achievements in academia. In general, the existing methods for Androi
剩余内容已隐藏，支付完成后下载完整资料
资料编号：[253837]，资料为PDF文档或Word文档，PDF文档可免费转换为Word
以上是毕业论文外文翻译，课题毕业论文、任务书、文献综述、开题报告、程序设计、图纸设计等资料可联系客服协助查找。
