检索结果-内蒙古大学图书馆

23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Hou, Shifu Ye, Yanfang Song, Yangqiu Abdulhayoglu, Melih West Virginia Univ Dept CSEE Morgantown WV 26506 USA HKUST Dept CSE Hong Kong Peoples R China Comodo Secur Solut Inc Clinton NY USA

ISBN: (纸本)9781450348874

With explosive growth of android malware and due to the severity of its damages to smart phone users, the detection of android malware has become increasingly important in cybersecurity. The increasing sophistication of android malware calls for new defensive techniques that are capable against novel threats and harder to evade. In this paper, to detect android malware, instead of using Application Programming Interface (API) calls only, we further analyze the different relationships between them and create higher-level semantics which require more efforts for attackers to evade the detection. We represent the android applications (apps), related APIs, and their rich relationships as a structured heterogeneous information network (HIN). Then we use a meta path based approach to characterize the semantic relatedness of apps and APIs. We use each meta-path to formulate a similarity measure over android apps, and aggregate different similarities using multi-kernel learning. Then each meta-path is automatically weighted by the learning algorithm to make predictions. To the best of our knowledge, this is the first work to use structured HIN for android malware detection. Comprehensive experiments on real sample collections from Comodo Cloud Security Center are conducted to compare various malware detection approaches. Promising experimental results demonstrate that our developed system HinDroid outperforms other alternative android malware detection techniques.

关键词： android malware detection Application Programming Interface Calls Relation Analysis Heterogeneous Information Network

来源：评论

学校读者我要写书评

暂无评论

An android malware detection System Based on Behavior Comparison Analysis 17th

An Android Malware Detection System Based on Behavior Compar...

引用

17th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Tao, Jing Zhang, Yan Cao, Pengfei Wang, Zheng Zhao, Qiqi Xi An Jiao Tong Univ Minist Educ Key Lab Intelligent Networks & Network Secur Xian 710049 Peoples R China

ISBN: (纸本)9783319654829;9783319654812

At present, android malwares become more and more subtle and intelligent, after their invasion, they often detect whether the running environment is a real environment, to decide whether to perform their malicious behavior. Therefore, malware tend to execute different behavior when running in different environments. Benign applications will perform the same functions in different environments, their behaviors have a strong consistency. Based on this basic idea, we design an android malware detection method based on behavior comparison analysis. First, design and development a number of specific different running environments, and then execute application in these environments. With the same event input, record and compare the behaviors of this application, calculate the difference, determine whether it is malicious. Under the guidance of this thought, we design and development the android malware detection system EmuProtect. We evaluate EmuProtect system from the aspects of accuracy and validity, the results show that this system can effectively detect android malicious applications.

关键词： android malware detection android application behavior model Behavior analysis

来源：评论

学校读者我要写书评

暂无评论

XGBoost-Based android malware detection 13

XGBoost-Based Android Malware Detection

引用

13th International Conference on Computational Intelligence and Security (CIS)

作者： Wang, Jiong Li, Boquan Zeng, Yuwei Chinese Acad Sci Inst Informat Engn Beijing 100093 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China

ISBN: (纸本)9781538648223

malware remains the most significant security threat to smartphones in spite of the constantly upgrading of the system. In this paper, we introduce an android malware detection method based on XGBoost model. We subsequently discuss the effect of feature selection on the classification. In the end, we verify the high efficacy and good accuracy of this model through the experiment, which achieves similar results to the SVM while spending less time.

关键词： android malware detection static analysis machine learning XGBoost random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

android malware detection Using Local Binary Pattern and Principal Component Analysis

Android Malware Detection Using Local Binary Pattern and Pri...

引用

The Third International Conference of Pioneering Computer Scientists, Engineers and Educators,ICPCSEE 2017(originally ICYCSEE)

作者： Qixin Wu Zheng Qin Jinxin Zhang Hui Yin Guangyi Yang Kuangsheng Hu College of Computer Science and Electronic Engineering Hunan University Hunan Key Laboratory of Big Data Research and Application Hunan Institute of Metrology and Test

Nowadays, analysis methods based on big data have been widely used in malicious software detection. Since android has become the dominator of smartphone operating system market, the number of android malicious applications are increasing rapidly as well, which attracts attention of malware attackers and researchers alike. Due to the endless evolution of the malware, it is critical to apply the analysis methods based on machine learning to detect malwares and stop them from leakaging our privacy information. In this paper, we propose a novel android malware detection method based on binary texture feature recognition by Local Binary Pattern and Principal Component Analysis, which can visualize malware and detect malware accurately. Also,our method analyzes malware binary directly without any decompiler,sandbox or virtual machines, which avoid time and resource consumption caused by decompiler or monitor in this process. Experimentation on 5127 benigns and 5560 malwares shows that we obtain a detection accuracy of 90%.

关键词： android malware detection Binary texture feature Local binary pattern Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-synthetic minority oversampling technique: Oversampling based on fuzzy set theory for android malware detection in imbalanced datasets

引用

INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS 2017年第4期13卷 1-15页

作者： Xu, Yanping Wu, Chunhua Zheng, Kangfeng Niu, Xinxin Yang, Yixian Beijing Univ Posts & Telecommun Sch Comp Sci Beijing Peoples R China

In previous work, imbalanced datasets composed of more benign samples (the majority class) than the malicious one (the minority class) have been widely adopted in android malware detection. These imbalanced datasets bias learning toward the majority class, so that the minority class examples are more likely to be misclassified. To solve the problem, we propose a new oversampling method called fuzzy-synthetic minority oversampling technique, which is based on fuzzy set theory and the synthetic minority oversampling technique method. As the sample size of the majority class increases relative to that of the minority class, fuzzy-synthetic minority oversampling technique generates more synthetic examples for each minority class examples in the fuzzy region, where the minority examples have a low degree of membership to the minority class and are more likely to be misclassified. Using the new synthetic examples, the classifiers build larger decision regions that contain more minority examples, and they are no longer biased to the majority class. Compared with synthetic minority oversampling technique and Borderline-synthetic minority oversampling technique methods, fuzzy-synthetic minority oversampling technique achieves higher accuracy on both the minority class and the entire datasets.

关键词： Fuzzy-synthetic minority oversampling technique imbalanced datasets oversample fuzzy region android malware detection

来源：评论

学校读者我要写书评

暂无评论

Feature Selection to Mine Joint Features from High-dimension Space for android malware detection

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2017年第9期11卷 4658-4679页

作者： Xu, Yanping Wu, Chunhua Zheng, Kangfeng Niu, Xinxin Lu, Tianling Beijing Univ Posts & Telecommun Sch Cyberspace Secur Beijing 100876 Peoples R China Peoples Publ Secur Univ China Sch Informat Technol & Network Secur Beijing 100038 Peoples R China

android is now the most popular smartphone platform and remains rapid growth. There are huge number of sensitive privacy information stored in android devices. Kinds of methods have been proposed to detect android malicious applications and protect the privacy information. In this work, we focus on extracting the fine-grained features to maximize the information of android malware detection, and selecting the least joint features to minimize the number of features. Firstly, permissions and APIs, not only from android permissions and SDK APIs but also from the developer-defined permissions and third-party library APIs, are extracted as features from the decompiled source codes. Secondly, feature selection methods, including information gain (IG), regularization and particle swarm optimization (PSO) algorithms, are used to analyze and utilize the correlation between the features to eliminate the redundant data, reduce the feature dimension and mine the useful joint features. Furthermore, regularization and PSO are integrated to create a new joint feature mining method. Experiment results show that the joint feature mining method can utilize the advantages of regularization and PSO, and ensure good performance and efficiency for android malware detection.

关键词： android malware detection feature selection joint features particle swarm optimization regularization

来源：评论

学校读者我要写书评

暂无评论

A study of android malware detection techniques in virtual environment

引用

Cluster Computing-The Journal of Networks Software Tools and Applications 2016年第4期19卷 2295-2304页

作者： Jung, Hyun Mi Kim, Ki-Bong Cho, Han-Jin KISTI Dept Supercomp Syst Dev 245 Daehangno Yuseong Daejeon South Korea Daejeon Hlth Inst Technol Dept Comp & Informat 21 Chungjeong Ro Daejeon South Korea Far E Univ Dept Smart Mobile 76-32 Daehak Gil Gamgok Myeon Eumseong Gun Chungcheongbuk South Korea

With the rapid development of mobile environment, cyber-attacks have become more commonplace and more sophisticated. In smartphone operating system market, in particular, android platform accounts for a large portion (65 % or higher). At the same time, malwares on the android platform, has increased exponentially. This, such as mobile Internet service provider (ISP) operator and device manufacturers, have applied an anti-virus product. However, there exhibit a high false-positive rate to detect malwares because these are based on patterns or heuristic. To solve this problem, this study proposed and implemented android malware detection techniques in virtual environment, using single physical machine. The proposed system is divided into a host system and virtual environment. The former features black market crawler designed to collect malware, hypervisor targeted for the communication and control of virtual machine and host machine and main module which transmits analysis file and result log to each system. In virtual environment, agent and emulator were implemented to analyze malware-suspicious application. This study implemented more active and faster android malware detection techniques through black market crawling and Linux kernel-hooking mechanism.

关键词： android malware Virtual machine Analysis android malware android malware detection

来源：评论

学校读者我要写书评

暂无评论

An android malware detection Approach Using Bayesian Inference 16

An Android Malware Detection Approach Using Bayesian Inferen...

引用

IEEE International Conference on Computer and Information Technology (CIT)

作者： Liu, Che-Hsun Zhang, Zhi-Jie Wang, Sheng-De Natl Taiwan Univ Grad Inst Elect Engn Taipei 10617 Taiwan

ISBN: (纸本)9781509043149

android malware detection has been a popular research topic due to non-negligible amount of malware targeting the android operating system. In particular, the naive Bayes generative classifier is a common technique widely adopted in many papers. However, we found that the naive Bayes classifier performs badly in Contagio malware Dump dataset, which could result from the assumption that no feature dependency exists. In this paper, we propose a lightweight method for android malware detection, which improves the performance of Bayesian classification on the Contagio malware Dump dataset. It performs static analysis to gather malicious features from an application, and applies principal component analysis to reduce the dependencies among them. With the hidden naive Bayes model, we can infer the identity of the application. In an evaluation with 15,573 normal applications and 3,150 malicious samples, our work detects 94.5% of the malware with a false positive rate of 1.0%. The experiment also shows that our approach is feasible on smartphones.

关键词： Static Analysis android malware detection Bayesian Inference Machine Learning

来源：评论

学校读者我要写书评

暂无评论

DroidDelver: An android malware detection System Using Deep Belief Network Based on API Call Blocks 17th

DroidDelver: An Android Malware Detection System Using Deep ...

引用

17th International Conference on Web-Age Information Management (WAIM)

作者： Hou, Shifu Saas, Aaron Ye, Yanfang Chen, Lifei West Virginia Univ Dept Comp Sci & Elect Engn Morgantown WV 26506 USA Fujian Normal Univ Sch Math & Comp Sci Fuzhou 350117 Peoples R China

ISBN: (纸本)9783319471211;9783319471204

Because of the explosive growth of android malware and due to the severity of its damages, the detection of android malware has become an increasing important topic in cyber security. Currently, the major defense against android malware is commercial mobile security products which mainly use signature-based method for detection. However, attackers can easily devise methods, such as obfuscation and repackaging, to evade the detection, which calls for new defensive techniques that are harder to evade. In this paper, resting on the analysis of Application Programming Interface (API) calls extracted from the smali files, we further categorize the API calls which belong to the some method in the smali code into a block. Based on the generated code blocks, we then apply a deep learning framework (i.e., Deep Belief Network) for newly unknown android malware detection. Using a real sample collection from Comodo Cloud Security Center, a comprehensive experimental study is performed to compare various malware detection approaches. Promising experimental results demonstrate that DroidDelver which integrates our proposed method outperform other alternative android malware detection techniques.

关键词： android malware detection API call block Deep belief network

来源：评论

学校读者我要写书评

暂无评论

Proposed New Features to Improve android malware detection 8

Proposed New Features to Improve Android Malware Detection

引用

8th International Symposium on Telecommunications (IST)

作者： Vajdi, Mahdi Torkaman, Atefeh Bahrololum, Marjan Tadayon, M. H. Salajegheh, Afshin ITRC Tehran Iran Islamic Azad Univ ITRC South Tehran Branch Tehran Iran Islamic Azad Univ South Tehran Branch Tehran Iran

ISBN: (纸本)9781509034352

In recent years, android has become most popular and largest installed operating systems in smartphones. The openness capability of android applications let the users to easily download many applications from markets. Accordingly, a large number of malicious applications may be received carelessly. Developers publish their applications in a market place without regard to special considerations. On the other hand, low knowledge of the users in analyzing the risk of these applications, create further exploits on information and privacy. These malicious applications can perform unauthorized activities such as gaining access to user's sensitive information, camera, SMS, phone calls, etc. In this paper a system which help the users to identify malicious or benign installed apps is proposed. The mentioned system implements a hybrid model based on AdaBoost, J48 to classify installed applications. We evaluate our system with 11096 real data collected from OCS Lab which includes 2124 malware samples and the rest is benign. The proposed system by addition some technical features;the number of Services, Intent Filter and Broadcast Receivers can improve the average true positive rate from 98.9% to 99.2% (by using Gain ratio) and 96.8% to 98.1% (by using CFS).

关键词： android malware detection Hybrid Model Classification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：