Proceedings Article10.1109/ICSAI.2018.8599356
A Dynamic and Static Combined Android Malicious Code Detection Model based on SVM
Du Jinran,Chen Huajun,Weijie Zhon,Liu Zhen,Xu Aidong +4 more
- 01 Nov 2018
4
TL;DR: A dynamic and static combined Android malicious code detection model based on SVM, which proved the effectiveness of the method in detecting Android malware.
read more
Abstract: With the rapid spread of wireless networks and 4G networks, the application of mobile intelligent terminals has become more and more widespread. At the same time, there are more and more malicious software for mobile terminals, especially for the Android platform. Aiming at the detection problem of Android malicious code, a dynamic and static combined Android malicious code detection model based on SVM was proposed. Firstly, the dynamic and static features of Android program are extracted. Then, these features were vectored, used for the training and testing of SVM (Support vector machine). As shown in the experiments, the correct detection rate of Android malware is as high as 94.38%, recall rate achieving 98.46%, proved the effectiveness of the method.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Malicious application detection in android — A systematic literature review
Tejpal Sharma,Dhavleesh Rattan +1 more
TL;DR: This research will help to identify malicious applications in android operating system and new hybrid techniques must be implemented to investigate malware activities.
66
Machine Learning Algorithm for Malware Detection: Taxonomy, Current Challenges and Future Directions
TL;DR: In this article , a taxonomy of machine learning methods for malware detection is presented, which considers shortcomings in performance accuracy, analysis type, and malware detection approaches that fail to identify unexpected malware attacks.
27
Malicious Controller Detection Mechanism based on Graph Convolutional Neural Network
Yongan Guo,Hao Huang,Hao She,Yu'ao Wang +3 more
- 02 Nov 2023
TL;DR: A controller detection method that can effectively detect malicious controllers in the network and enhance the security and reliability of the network is proposed.
Predictive Feature Learning for Future Segmentation Prediction
Zihang Lin,Jiangxin Sun,Jian-Fang Hu,Qizhi Yu,Jian-Huang Lai,Wei-Shi Zheng +5 more
TL;DR: This work proposes Predictive Feature Autoencoder, a novel framework for future segmentation prediction, enhancing global structures and suppressing local details in latent features to improve prediction accuracy and outperform state-of-the-art methods.
References
•Proceedings Article
Hey, You, Get Off of My Market: Detecting Malicious Apps in Official and Alternative Android Markets
Yajin Zhou,Zhi Wang,Wu Zhou,Xuxian Jiang +3 more
- 01 Jan 2012
TL;DR: A permissionbased behavioral footprinting scheme to detect new samples of known Android malware families and a heuristics-based filtering scheme to identify certain inherent behaviors of unknown malicious families are proposed.
DroidMat: Android Malware Detection through Manifest and API Calls Tracing
Dong-Jie Wu,Ching-Hao Mao,Te-En Wei,Hahn-Ming Lee,Kuo-Ping Wu +4 more
- 09 Aug 2012
TL;DR: A static feature-based mechanism to provide a static analyst paradigm for detecting the Android malware and shows that the recall rate of the approach is better than one of well-known tool, Androguard, published in Black hat 2011, which focuses on Android malware analysis.
717
Apposcopy: semantics-based detection of Android malware through static analysis
Yu Feng,Saswat Anand,Isil Dillig,Alex Aiken +3 more
- 11 Nov 2014
TL;DR: The signature matching algorithm of Apposcopy uses a combination of static taint analysis and a new form of program representation called Inter-Component Call Graph to efficiently detect Android applications that have certain control- and data-flow properties.
DroidDetector: Android Malware Characterization and Detection Using Deep Learning
TL;DR: An online deep-learning-based Android malware detection engine (DroidDetector) that can automatically detect whether an app is a malware or not is implemented and shows that deep learning is suitable for characterizing Android malware and especially effective with the availability of more training data.
475
Review: Classification of malware based on integrated static and dynamic features
TL;DR: This paper presents the first classification method integrating static and dynamic features into a single test and concludes that to achieve acceptable accuracy in classifying the latest malware, some older malware should be included in the set of data.
290