Adversarial Samples on Android Malware Detection Systems for IoT Systems
Many IoT (Internet of Things) systems run Android systems or Android-like systems. With the continuous development of machine learning algorithms, the learning-based Android malware detection system for IoT devices has gradually increased. However, these learning-based detection models are often vul...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/4/974 |
| _version_ | 1828391044257939456 |
|---|---|
| author | Xiaolei Liu Xiaojiang Du Xiaosong Zhang Qingxin Zhu Hao Wang Mohsen Guizani |
| author_facet | Xiaolei Liu Xiaojiang Du Xiaosong Zhang Qingxin Zhu Hao Wang Mohsen Guizani |
| author_sort | Xiaolei Liu |
| collection | DOAJ |
| description | Many IoT (Internet of Things) systems run Android systems or Android-like systems. With the continuous development of machine learning algorithms, the learning-based Android malware detection system for IoT devices has gradually increased. However, these learning-based detection models are often vulnerable to adversarial samples. An automated testing framework is needed to help these learning-based malware detection systems for IoT devices perform security analysis. The current methods of generating adversarial samples mostly require training parameters of models and most of the methods are aimed at image data. To solve this problem, we propose a testing framework for learning-based Android malware detection systems (TLAMD) for IoT Devices. The key challenge is how to construct a suitable fitness function to generate an effective adversarial sample without affecting the features of the application. By introducing genetic algorithms and some technical improvements, our test framework can generate adversarial samples for the IoT Android application with a success rate of nearly 100% and can perform black-box testing on the system. |
| first_indexed | 2024-12-10T06:56:25Z |
| format | Article |
| id | doaj.art-85d96da2e7ee47a78529a0bc17e40da6 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-12-10T06:56:25Z |
| publishDate | 2019-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-85d96da2e7ee47a78529a0bc17e40da62022-12-22T01:58:26ZengMDPI AGSensors1424-82202019-02-0119497410.3390/s19040974s19040974Adversarial Samples on Android Malware Detection Systems for IoT SystemsXiaolei Liu0Xiaojiang Du1Xiaosong Zhang2Qingxin Zhu3Hao Wang4Mohsen Guizani5School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaDepartment of Computer and Information Sciences, Temple University, Philadelphia, PA 19122, USASchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, ChinaDepartment of Computer Science, Norwegian University of Science and Technology, 7491 Trondheim, NorwayDepartment of Computer Science and Engineering, Qatar University, Doha 2713, QatarMany IoT (Internet of Things) systems run Android systems or Android-like systems. With the continuous development of machine learning algorithms, the learning-based Android malware detection system for IoT devices has gradually increased. However, these learning-based detection models are often vulnerable to adversarial samples. An automated testing framework is needed to help these learning-based malware detection systems for IoT devices perform security analysis. The current methods of generating adversarial samples mostly require training parameters of models and most of the methods are aimed at image data. To solve this problem, we propose a testing framework for learning-based Android malware detection systems (TLAMD) for IoT Devices. The key challenge is how to construct a suitable fitness function to generate an effective adversarial sample without affecting the features of the application. By introducing genetic algorithms and some technical improvements, our test framework can generate adversarial samples for the IoT Android application with a success rate of nearly 100% and can perform black-box testing on the system.https://www.mdpi.com/1424-8220/19/4/974Internet of Thingsmalware detectionadversarial samplesmachine learning |
| spellingShingle | Xiaolei Liu Xiaojiang Du Xiaosong Zhang Qingxin Zhu Hao Wang Mohsen Guizani Adversarial Samples on Android Malware Detection Systems for IoT Systems Sensors Internet of Things malware detection adversarial samples machine learning |
| title | Adversarial Samples on Android Malware Detection Systems for IoT Systems |
| title_full | Adversarial Samples on Android Malware Detection Systems for IoT Systems |
| title_fullStr | Adversarial Samples on Android Malware Detection Systems for IoT Systems |
| title_full_unstemmed | Adversarial Samples on Android Malware Detection Systems for IoT Systems |
| title_short | Adversarial Samples on Android Malware Detection Systems for IoT Systems |
| title_sort | adversarial samples on android malware detection systems for iot systems |
| topic | Internet of Things malware detection adversarial samples machine learning |
| url | https://www.mdpi.com/1424-8220/19/4/974 |
| work_keys_str_mv | AT xiaoleiliu adversarialsamplesonandroidmalwaredetectionsystemsforiotsystems AT xiaojiangdu adversarialsamplesonandroidmalwaredetectionsystemsforiotsystems AT xiaosongzhang adversarialsamplesonandroidmalwaredetectionsystemsforiotsystems AT qingxinzhu adversarialsamplesonandroidmalwaredetectionsystemsforiotsystems AT haowang adversarialsamplesonandroidmalwaredetectionsystemsforiotsystems AT mohsenguizani adversarialsamplesonandroidmalwaredetectionsystemsforiotsystems |