检索结果-内蒙古大学图书馆

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

android malware detection as a Bi-level problem

引用

COMPUTERS & SECURITY 2022年 121卷

作者： Jerbi, Manel Dagdia, Zaineb Chelly Bechikh, Slim Ben Said, Lamjed Univ Tunis SMART Lab ISG Campus Tunis Tunisia Univ Paris Saclay UVSQ DAVID Gif Sur Yvette France Inst Super Gest Tunis LARODEC Tunis Tunisia

malware detection is still a very challenging topic in the cybersecurity field. This is mainly due to the use of obfuscation techniques. To solve this issue, researchers proposed to extract frequent API (Application Programming Interface) call sequences and then use them as behavior indicators. Several methods aiming at generating malware detection rules have been proposed with the goal to come up with a set of rules that is able to accurately detect malicious code patterns. However, the rules generation process heavily depends on the training database content which will affect the detection rate of the model when confronted to new variants of malicious patterns. In order to assess a rule's detection accuracy, we need to execute the rule on the whole malware database which makes the detection rule quality evaluation very sensitive to the database content. To solve this issue, we suggest in this paper to consider the detection rules generation process as a GLOP (Bi-Level Optimization Problem), where a lower-level optimization task is embedded within the upper-level one. The goal of the upper-level is to generate a set of detection rules in the form of: trees of combined patterns. Those rules are able to detect not only the real patterns from the base of examples but also the artificial patterns generated by the lower-level. The lower-level aims to generate a set of artificial malicious patterns that escape the rules of the upper-level. An efficient co-evolutionary algorithm is adopted as a search engine to ensure optimization at both levels. Such an automated competition between the two levels makes our new method BMD (Bi-level malware detection) able to produce effective detection rules that are capable of detecting new predictable malicious behaviors in addition to existing ones. Based on the statistical analysis of the experimental results, our BMD method has shown its merits when compared to several relevant state-of-the-art malware detection techniques on differ

关键词： android malware detection Bi-level optimization detection rules generation Artificial malicious patterns Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF FEATURES SELECTION AND MACHINE LEARNING CLASSIFIER IN android malware detection

ANALYSIS OF FEATURES SELECTION AND MACHINE LEARNING CLASSIFI...

引用

5th International Conference on Information Science and Applications (ICISA)

作者： Mas'ud, Mohd Zaki Sahib, Shahrin Abdollah, Mohd Faizal Selamat, Siti Rahayu Yusof, Robiah Univ Teknikal Malaysia Melaka Fac Informat Technol & Commun Durian Tunggal 76100 Melaka Malaysia

ISBN: (纸本)9781479944415

The proliferation of android-based mobile devices and mobile applications in the market has triggered the malware author to make the mobile devices as the next profitable target. With user are now able to use mobile devices for various purposes such as web browsing, ubiquitous services, online banking, social networking, MMS and etc, more credential information is expose to exploitation. Applying a similar security solution that work in Desktop environment to mobile devices may not be proper as mobile devices have a limited storage, memory, CPU and power consumption. Hence, there is a need to develop a mobile malware detection that can provide an effective solution to defence the mobile user from any malicious threat and at the same time address the limitation of mobile devices environment. Prior to this matter, this research focused on evaluating the best features selection to be used in the best machine-learning classifiers. To find the best combination of both features selection and classifier, five sets of different feature selection are applies to five different machine learning classifiers. The classifier outcome is evaluated using the True Positive Rate (TPR), False Positive Rate (FPR), and Accuracy. The best combination of both features selection and classifier can be used to reduce features selection and at the same time able to classify the infected android application accurately.

关键词： Mobile malware android android malware detection Feature Selection Machine Learning

来源：评论

学校读者我要写书评

暂无评论

SADroid: A Deep Classification Model for android malware detection Based on Semantic Analysis

SADroid: A Deep Classification Model for Android Malware Det...

引用

IEEE Wireless Communications and Networking Conference (IEEE WCNC)

作者： Zhu, Dali Xi, Tong Jing, Pengfei Xia, Qing Wu, Di Zhang, Yiming Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing Peoples R China

ISBN: (数字)9781728131061

ISBN: (纸本)9781728131061

Previous works have designed many deep learning models for android malware detection using various features (e.g. permissions, APIs et.) to achieve better classification performance. However, these methods usually input each feature into the classifier independently and completely (using One-Hot Encoding) so that features are orthogonal to each other. This discrete representation is difficult to preserve the semantic information of features. In this paper, we design two feature segmentation methods to enhance the semantics of the features in preprocessing. Besides that, we propose a malware detection model that consists of a distributed representation process for android features and an optimized convolutional neural network for classification, named Semantic Analysis detection (SADroid). In SADroid, the distance between features with similar semantics is closer in vector space. It provides the semantic information of features to the classifier to improve the classification performance. In the evaluation, SADroid outperforms the advanced models in detection accuracy on a data set of 19,600 applications, while maintaining a low computational cost.

关键词： Deep learning android malware detection Semantic information Distributed representation

来源：评论

学校读者我要写书评

暂无评论

Enhanced android malware detection: An SVM-based Machine Learning Approach

Enhanced Android Malware Detection: An SVM-based Machine Lea...

引用

IEEE International Conference on Big Data and Smart Computing (BigComp)

作者： Han, Hyoil Lim, SeungJin Suh, Kyoungwon Park, Seonghyun Cho, Seong-je Park, Minkyu Illinois State Univ Sch Informat Technol Normal IL 61761 USA Merrimack Coll Dept Comp Sci N Andover MA 01845 USA Dankook Univ Dept Appl Comp Engn Yongin South Korea Dankook Univ Dept Comp Sci & Engn Yongin South Korea Konkuk Univ Dept Software Technol Chungju South Korea

ISBN: (纸本)9781728160344

The cybersecurity of increasing numbers of mobile devices and their users are threatened by malicious applications. Detecting malicious android applications is a challenge due to the massive number of android applications and their various properties which provide a large set of features and a sparse dataset. We focus on the resources the android applications call and employ the Application Program Interface (API) calls as features. The dataset used in this work is from an android environment where malicious and benign applications frequently access the system resources through android API calls. Since an android application would invoke a relatively small number of APIs in ordinary scenarios, data in the dataset is inherently sparse and high dimensional. We experimented intensively with 58,602 android applications as well as 133,227 features (i.e., API Calls). This paper presents a machine-learning-based approach using Support Vector Machines (SVM) to detect malicious android applications;the new approach delivers results highly competitive with existing approaches.

关键词： android malware detection API Calls Support Vector Machines Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Defensive Randomization Against Adversarial Attacks in Image-based android malware detection

Defensive Randomization Against Adversarial Attacks in Image...

引用

IEEE International Conference on Communications (IEEE ICC)

作者： Lan, Tianwei Darwaish, Asim Nait-Abdesselam, Farid Gu, Pengwenlong Univ Paris Cite Paris France Univ Missouri Kansas City MO 64110 USA Inst Polytech Paris Telecom Paris LTCI Paris France

ISBN: (纸本)9781538674628

The extensive popularity of android operating system hones the increased malware attacks and threatens the android ecosystem. Machine learning is one of the versatile tools to detect legacy and new malware with high accuracy. However, these Machine Learning (ML) models are vulnerable to adversarial attacks, which severely threaten their cybersecurity deployment. To combat the deterrence of ML models against adversarial attacks, we propose a novel randomization method as a defense for image-based detection systems. In addition to defensive randomization, the paper also introduces a novel method, called AutoE, for transforming an APK to an image by leveraging API calls only. To evaluate the effectiveness of randomization as a defense against adversarial settings, we compare our AutoE with two state-of-the-art image-based android malware detection systems. The experimental results reveal that the randomization is a strong defensive hood for image-based android malware detection systems against adversarial attacks. Moreover, our novel AutoE detects malware with 96% accuracy and the randomization approach makes it harder against adversarial attacks.

关键词： Adversarial Attacks and Defense Deep Learning android malware detection Randomization

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Video-Classification in android malware detection Through API-Streams and CNN-LSTM Autoencoders 5th

Effectiveness of Video-Classification in Android Malware Det...

引用

5th International Symposium on Mobile Internet Security (MobiSec)

作者： D'Angelo, Gianni Palmieri, Francesco Robustelli, Antonio Univ Salerno Dept Comp Sci Fisciano Italy

ISBN: (纸本)9789811695766;9789811695759

The outbreak of the COVID-19 pandemic has forced worldwide employees to massive use of their mobile devices to access corporate systems. This new scenario has made mobile devices more susceptible to malicious applications, which are yearly developed to conduct several hostile activities. Concerned about this fact, many Deep Learning (DL) based solutions have been proposed, in the last decade, by considering both static and dynamic approaches. However, static solutions are adversely affected by obfuscation techniques and polymorphic applications, while dynamic ones cannot reduce the damages caused during applications execution. To this purpose, the following paper aims to propose a novel approach called API-Streams to minimize damages at Run-time. Therefore, we investigate several Video-Classification tasks through CNN-LSTM Autoencoders (CNN-LSTM-AEs). More precisely, we combine the capability of AEs in finding compact features with the classification abilities of Deep Neural Networks (DNNs), and we show that the proposed approach achieves an average accuracy of 98% in the presence of several unbalanced training datasets. Finally, we use the t-Stochastic Neighbor Embedded (t-SNE) representation technique to investigate the abilities of the employed AE to cluster data into their respective classes by limiting their overlapping.

关键词： android malware detection API-Streams Autoencoders Video classification

来源：评论

学校读者我要写书评

暂无评论

An Analysis on Different Distance Measures in KNN with PCA for android malware detection 22

An Analysis on Different Distance Measures in KNN with PCA f...

引用

22nd International Conference on Advances in ICT for Emerging Regions (ICTer)

作者： Dissanayake, Sayuru Gunathunga, Sankha Jayanetti, Dimalka Perera, Kavindu Liyanapathirana, Chethana Rupasinghe, Lakmal Sri Lanka Inst Informat Technol Fac Comp Malabe Sri Lanka

ISBN: (纸本)9798350346138

As Majority of the market is presently occupied by android consumers, android operating system is a prominent target for intruders. This research shows a dynamic android malware detection approach that classifies dangerous and trustworthy applications using system call monitoring. While the applications were in the execution phase, dynamic system call analysis was conducted on legitimate and malicious applications. Majority of relevant machine learning-based studies on detecting android malware frequently employ baseline classifier settings and concentrate on selecting either the best attributes or classifier. This study examines the performance of K Nearest Neighbor (KNN), factoring its many hyper-parameters with a focus on various distance metrics and this paper shows performance of KNN before and after performing Principal Component Analysis (PCA). The findings demonstrate that the classification performance may be significantly improved by using the adequate distance metric. KNN algorithm shows decent accuracy and improvement of efficiency such as decreasing the training time After PCA.

关键词： android System Calls K Nearest Neighbor Principal Component analysis android malware detection

来源：评论

学校读者我要写书评

暂无评论

MalWhiteout: Reducing Label Errors in android malware detection 7

MalWhiteout: Reducing Label Errors in Android Malware Detect...

引用

37th IEEE/ACM International Conference on Automated Software Engineering (ASE)

作者： Wang, Liu Wang, Haoyu Luo, Xiapu Sui, Yulei Huazhong Univ Sci & Technol Sch Cyber Sci & Engn Wuhan Peoples R China Hong Kong Polytechn Univ Hong Kong Peoples R China Univ Technol Sydney Sydney NSW Australia

ISBN: (纸本)9781450394758

Machine learning based android malware detection has attracted a great deal of research work in recent years. A reliable malware dataset is critical to evaluate the effectiveness of malware detection approaches. Unfortunately, existing malware datasets used in our community are mainly labelled by leveraging existing anti-virus services (i.e., VirusTotal), which are prone to mislabelling. This, however, would lead to the inaccurate evaluation of the malware detection techniques. Removing label noises from android malware datasets can be quite challenging, especially at a large data scale. To address this problem, we propose an effective approach called MalWhiteout to reduce label errors in android malware datasets. Specifically, we creatively introduce Confident Learning (CL), an advanced noise estimation approach, to the domain of android malware detection. To combat false positives introduced by CL, we incorporate the idea of ensemble learning and inter-app relation to achieve a more robust capability in noise detection. We evaluate MalWhiteout on a curated large-scale and reliable benchmark dataset. Experimental results show that MalWhiteout is capable of detecting label noises with over 94% accuracy even at a high noise ratio (i.e., 30%) of the dataset. MalWhiteout outperforms the state-of-the-art approach in terms of both effectiveness (8% to 218% improvement) and efficiency (70 to 249 times faster) across different settings. By reducing label noises, we show that the performance of existing malware detection approaches can be improved.

关键词： label noise android malware detection confident learning

来源：评论

学校读者我要写书评

暂无评论

An Image-inspired and CNN-based android malware detection Approach 34

An Image-inspired and CNN-based Android Malware Detection Ap...

引用

34th IEEE/ACM International Conference on Automated Software Engineering (ASE)

作者： Yang, Shao Case Western Reserve Univ Dept Elect Engn & Comp Sci Cleveland OH 44106 USA

ISBN: (纸本)9781728125084

Until 2017, android smartphones occupied approximately 87% of the smartphone market. The vast market also promotes the development of android malware. Nowadays, the number of malware targeting android devices found daily is more than 38,000. With the rapid progress of mobile application programming and anti-reverse-engineering techniques, it is harder to detect all kinds of malware. To address challenges in existing detection techniques, such as data obfuscation and limited codes coverage, we propose a detection approach that directly learns features of malware from Dalvik bytecode based on deep learning technique (CNN). The average detection time of our model is 0.22 seconds, which is much lower than other existing detection approaches. In the meantime, the overall accuracy of our model achieves over 93%.

关键词： android malware detection CNN Deep learning

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：