Deep neural architectures for large scale android malware analysis

Nauman, Mohammad; Tanveer, Tamleek Ali; Khan, Sohail; Syed, Toqeer Ali

doi:10.1007/s10586-017-0944-y

Cited by 34 publications

(21 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The comparison of the proposed model in this work with studies using different and up-to-date approaches is summarized in Table-2. When the results of known android malware detection tools such as Drebin [22], RevealDroid [28], Nauman [29], ProDroid [14], DL-Droid [30], Maldozer [31] were examned, although some studies obtained low classification rates, in general an accuracy of 95% and above has been achieved.…”

Section: Comparison With Other Proposed Frameworkmentioning

confidence: 99%

AFWDroid: Android Kötücül Yazılım Tespitinde Derin Özellik Çıkarımı ve Ağırlıklandırma

Arslan¹,

Ölmez²,

Er³

2021

DÜMF Mühendislik Dergisi

View full text Add to dashboard Cite

Android malware detection is a critical and important problem that must be solved for a widely used operating system. Conventional machine learning techniques first extract some features from applications, then create classifiers to distinguish between malicious and benign applications. Most of the studies available today ignore the weighting of the obtained features. To overcome this problem, this study proposes a new software detection method based on weighting the data in feature vectors to be used in classification. To this end, firstly, the manifest file was read from the Android application package. Different features such as activities, services, permissions were extracted from the file, and for classification, a selection was made among these features. The parameters obtained as a result of selection were optimized by the deep neural network model. Studies revealed that through feature selection and weighting, better performance values could be achieved and more competitive results could be obtained in weight-sensitive classification.

show abstract

Section: Comparison With Other Proposed Frameworkmentioning

confidence: 99%

AFWDroid: Android Kötücül Yazılım Tespitinde Derin Özellik Çıkarımı ve Ağırlıklandırma

Arslan¹,

Ölmez²,

Er³

2021

DÜMF Mühendislik Dergisi

View full text Add to dashboard Cite

show abstract

“…It has been observed that damaged vehicles are slightly different than those with their original color. However, human eyes cannot perceive those differences and hence, for this purpose, the proposed system uses Fully Connected Neural Network and Convolutional Neural Network which are state of the art machine learning models used in pattern recognition [67]- [70]. Similarly, for the prediction of vehicle prices through mileage traveled, the proposed system uses a regression model.…”

Section: ) Prediction Modelsmentioning

confidence: 99%

A Novel Blockchain-Based Framework for Vehicle Life Cycle Tracking: An End-to-End Solution

et al. 2020

Self Cite

View full text Add to dashboard Cite

Transactions related to vehicles include manufacturing, buying, selling, paying insurance(takaful), obtaining regular inspection, leasing a vehicle from banks, getting in an accident, engaging in a traffic violation, calculating price predictions and renting a vehicle. Many people perform transactions related to vehicles in their daily life; transportation authorities also perform vehicle transactions as part of managing vehicle fleets. But tracking these transactions is a challenging task. There are countrywide solutions that uses centralized systems. However, these solutions have problems with trust management, transparency, and access control. Therefore, we believe there is still room for integrated automation of various vehicle-related transactions. In this paper, we present a blockchainbased framework for vehicle tracking that incorporates the mentioned features. Moreover, blockchain is customized to enable usage control for additional transactions, such as inspection, renting and islamic insurance. The usage control model is integrated with IoT devices to continuously monitor the vehicles for certain conditions and remotely revoke access if needed [1]. The complete transaction set is recorded over an immutable ledger that provides trust, transparency and a complete history of record. In this paper, we also presents a prototype implementation of a permissioned blockchain, which will be made available under the GNUv3 General Public License. Performance analysis is performed on the newly proposed framework implementation over the permissioned blockchain to measure its adoption and suitability. INDEX TERMS Blockchain, decentralized applications, smart contracts, vehicle life cycle tracking VOLUME 4, 2016 This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.

show abstract

“…Nauman et al [13], used more than one neural network models to perform Android malware analysis. Authors used fully-connected neural network, CNN, RNN & Long Short-Term Memory (LSTM), Autoencoders and DBN.…”

Section: Recurrent Neural Network Based Systemmentioning

confidence: 99%

Analysis of Android Malware Detection Techniques in Deep Learning

Agarwal¹,

Jain²,

Ranjan³

2020

SKIT Research Journal

View full text Add to dashboard Cite

Over the years, developments in smart phone technology has boost up their use among users. This has captivated malware authors' attention. Malware attacks in various forms has troubled users by stealing their personal information, banking information and much more. Android users have been strained most because of Android's open nature. Throughout this time, efforts have been made to devise software and methods to detect android malwares. Starting from anti-virus software to Machine Learning and now Deep Learning, researchers have put forward various techniques to get to grips with the problem. Many Deep Learning Techniques have been put forward like Deep Neural Network, Convolutional Neural Network, Recurrent Neural Network, Deep Belief Network and Autoencoders. This paper looks at and analyzes supervised Deep Learning classifiers to detect Android malware.

show abstract

Deep neural architectures for large scale android malware analysis

Cited by 34 publications

References 32 publications

AFWDroid: Android Kötücül Yazılım Tespitinde Derin Özellik Çıkarımı ve Ağırlıklandırma

AFWDroid: Android Kötücül Yazılım Tespitinde Derin Özellik Çıkarımı ve Ağırlıklandırma

A Novel Blockchain-Based Framework for Vehicle Life Cycle Tracking: An End-to-End Solution

Analysis of Android Malware Detection Techniques in Deep Learning

Contact Info

Product

Resources

About