scholarly journals Deep Learning Based Static Analysis of Malwares in Android Applications

2021 ◽  
Author(s):  
Nivedha K ◽  
Indra Gandhi K ◽  
Shibi S ◽  
Nithesh V ◽  
Ashwin M
Keyword(s):  
Operating System ◽  
Deep Learning ◽  
Open Source ◽  
Text Messages ◽  
Third Party ◽  
Android Application ◽  
Android Malware ◽  
Android Apps ◽  
User Data ◽  
Android Applications

Android is a widely distributed mobile operating system developed especially for mobile devices with touch screens. It is an open source, Google-distributed Linux-based mobile operating system. Since Android is open source, it enables Android devices to be targeted effectively by malware developers. Third-party markets do not search for malicious applications in their databases, so installing Android Application Packages (APKs) from these uncontrolled market places is often risky. Without user’s notice, these malware infected applications gain access to private user data, send text messages that costs the user, or hide malware apk file inside another application. The total number of new samples of Android malware amounted to 482,579 per month as of March 2020. In this paper deep learning approach that focuses on malware detection in android apps to protect data on user devices. We use different static features that are present in an Android application for the implementation of the proposed system. The system extracts various static features and gives them to the classifier for deep learning and shows the results. This proposed system will assist users in checking applications that are not downloaded from the official market.

scholarly journals Visual Detection for Android Malware using Deep Learning

2020 ◽  
Vol 10 (1) ◽  
pp. 152-156
Keyword(s):  
Deep Learning ◽  
Main Idea ◽  
Mobile Internet ◽  
Android Application ◽  
Analysis Model ◽  
Android Malware ◽  
Proposed Model ◽  
Learning Technique ◽  
Android Applications ◽  
High Level

The most serious threats to the current mobile internet are Android Malware. In this paper, we proposed a static analysis model that does not need to understand the source code of the android applications. The main idea is as most of the malware variants are created using automatic tools. Also, there are special fingerprint features for each malware family. According to decompiling the android APK, we mapped the Opcodes, sensitive API packages, and high-level risky API functions into three channels of an RGB image respectively. Then we used the deep learning technique convolutional neural network to identify Android application as benign or as malware. Finally, the proposed model succeeds to detect the entire 200 android applications (100 benign applications and 100 malware applications) with an accuracy of over 99% as shown in experimental results.

scholarly journals Detection and Prevention of Malware in Android Operating System

2021 ◽  
Vol 40 (4) ◽  
pp. 847-859
Author(s):  
Kashif Ali Dahri ◽  
Muhammad Saleem Vighio ◽  
Baqar Ali Zardari
Keyword(s):  
Operating System ◽  
Private Information ◽  
Malicious Code ◽  
The Internet ◽  
End User ◽  
Android Malware ◽  
Novel Approach ◽  
User Data ◽  
Android Applications ◽  
Android Operating System

The Internet is not safe anymore, malware can be discovered anywhere on the Internet. The risk of malware has increased also due to the increasing popularity and use of Smartphones and their underlying cost-free applications. With its great market share, the Android operating system has become a prime target for malware developers. When an Android phone is injected with a malware, it may result in compromising the privacy of the user by stealing sensitive and private information like contacts, ids, passwords, photos, call records, and so on. Compared to any other Android-based application category, games are the most preferred zone for attackers, due to the high interest of users in game applications. When an end user downloads a game, which is injected with malicious code, user data is infected without bringing in the knowledge of the user. Though, there still are not sufficient protection mechanisms or guidelines stated for end user against Android malware, this study offers a novel approach to detect Android malware in order to ensure the safe usage of Android applications. The advantage of this approach is its ability to utilize Android manifest files for the detection of malware. The availability of manifest file in every Android application makes this approach applicable to all Android applications. It can also be considered as a lightweight method for malware detection, and its efficiency is experimentally confirmed by testing and comparing the results of 50 Android games samples. Experiments are carried out using the Android Package Kit (APK) tools, and based on the experiments, different kinds of malware identification and prevention guidelines have been proposed for the safe and secure usage of the Android operating system.

scholarly journals A State of Art Survey for Understanding Malware Detection Approaches in Android Operating System

2021 ◽  
pp. 44-60
Author(s):  
Suhaib Jasim Hamdi ◽  
Naaman Omar ◽  
Adel AL-zebari ◽  
Karwan Jameel Merceedi ◽  
Abdulraheem Jamil Ahmed ◽  
...  
Keyword(s):  
Machine Learning ◽  
Operating System ◽  
Malware Detection ◽  
Personal Digital Assistants ◽  
Android Malware ◽  
Detection Techniques ◽  
Android Apps ◽  
Digital World ◽  
Android Malware Detection ◽  
Android Applications

Mobile malware is malicious software that targets mobile phones or wireless-enabled Personal digital assistants (PDA), by causing the collapse of the system and loss or leakage of confidential information. As wireless phones and PDA networks have become more and more common and have grown in complexity, it has become increasingly difficult to ensure their safety and security against electronic attacks in the form of viruses or other malware. Android is now the world's most popular OS. More and more malware assaults are taking place in Android applications. Many security detection techniques based on Android Apps are now available. Android applications are developing rapidly across the mobile ecosystem, but Android malware is also emerging in an endless stream. Many researchers have studied the problem of Android malware detection and have put forward theories and methods from different perspectives. Existing research suggests that machine learning is an effective and promising way to detect Android malware. Notwithstanding, there exist reviews that have surveyed different issues related to Android malware detection based on machine learning. The open environmental feature of the Android environment has given Android an extensive appeal in recent years. The growing number of mobile devices, they are incorporated in many aspects of our everyday lives. In today’s digital world most of the anti-malware tools are signature based which is ineffective to detect advanced unknown malware viz. Android OS, which is the most prevalent operating system (OS), has enjoyed immense popularity for smart phones over the past few years. Seizing this opportunity, cybercrime will occur in the form of piracy and malware. Traditional detection does not suffice to combat newly created advanced malware. So, there is a need for smart malware detection systems to reduce malicious activities risk. The present paper includes a thorough comparison that summarizes and analyses the various detection techniques.

scholarly journals Analysis of Permissions Correlation for Android Apps Using Statistical SVD Approach

2020 ◽  
Vol 8 (2) ◽  
pp. 10-19
Author(s):  
Zon Nyein Nway
Keyword(s):  
Private Information ◽  
Statistical Technique ◽  
Mobile App ◽  
Third Party ◽  
Risk Level ◽  
Android Malware ◽  
Android Apps ◽  
Android Applications ◽  
Value Decomposition ◽  
Almost All

Nowadays, almost all the users use Android applications in their smart phones for various reasons Since Android is free operating system, android-apps can be easily downloaded via biggest open app stores and third-party mobile app markets. But these applications were not guaranteed whether these are malware apps or not by legitimate organizations. As mobile phones are glued with most of the people, malware applications threaten all of them for their private information. So, the work of analysis for the apps is very important. The proposed system analyzes the correlation patterns of app’s permissions that must be used in all android apps by developers by using a statistical technique called singular value decomposition (SVD). The analysis phase uses the numbers of malware samples 50 to 300 from https://www.kaggle.com/goorax/static-analysis-of-android-malware-of-2017. The proposed system evaluates the risk level (High, Medium, and Low) of Android applications based on the correlation patterns of permissions. The system accuracy is 85% for both malware and goodware applications. Nowadays, almost all the users use Android applications in their smart phones for various reasons Since Android is free operating system, android-apps can be easily downloaded via biggest open app stores and third-party mobile app markets. But these applications were not guaranteed whether these are malware apps or not by legitimate organizations. As mobile phones are glued with most of the people, malware applications threaten all of them for their private information. So, the work of analysis for the apps is very important. The proposed system analyzes the correlation patterns of app’s permissions that must be used in all android apps by developers by using a statistical technique called singular value decomposition (SVD). The analysis phase uses the numbers of malware samples 50 to 300 from https://www.kaggle.com/goorax/static-analysis-of-android-malware-of-2017. The proposed system evaluates the risk level (High, Medium, and Low) of Android applications based on the correlation patterns of permissions. The system accuracy is 85% for both malware and goodware applications.

MackDroid - An Android based Application to monitor devices

2016 ◽  
Vol 9 ◽  
pp. 1
Author(s):  
Maaz Sirkhot ◽  
Ekta Sirwani ◽  
Aishwarya Kourani ◽  
Akshit Batheja ◽  
Kajal Jethanand Jewani
Keyword(s):  
Operating System ◽  
Open Source ◽  
Vital Role ◽  
Mobile Users ◽  
Android Application ◽  
Web Page ◽  
Technological World ◽  
Monitoring Service ◽  
User Friendly

In this technological world, smartphones can be considered as one of the most far-reaching inventions. It plays a vital role in connecting people socially. The number of mobile users using an Android based smartphone has increased rapidly since last few years resulting in organizations, cyber cell departments, government authorities feeling the need to monitor the activities on certain targeted devices in order to maintain proper functionality of their respective jobs. Also with the advent of smartphones, Android became one of the most popular and widely used Operating System. Its highlighting features are that it is user friendly, smartly designed, flexible, highly customizable and supports latest technologies like IoT. One of the features that makes it exclusive is that it is based on Linux and is Open Source for all the developers. This is the reason why our project Mackdroid is an Android based application that collects data from the remote device, stores it and displays on a PHP based web page. It is primarily a monitoring service that analyzes the contents and distributes it in various categories like Call Logs, Chats, Key logs, etc. Our project aims at developing an Android application that can be used to track, monitor, store and grab data from the device and store it on a server which can be accessed by the handler of the application.

A Commit Messages-Based Bug Localization for Android Applications

2019 ◽  
Vol 29 (04) ◽  
pp. 457-487 ◽  
Author(s):  
Tao Zhang ◽  
Wenjun Hu ◽  
Xiapu Luo ◽  
Xiaobo Ma
Keyword(s):  
Open Source ◽  
Software Maintenance ◽  
State Of The Art ◽  
Bug Localization ◽  
Two Phase ◽  
Android Apps ◽  
Bug Reports ◽  
Android Applications ◽  
The Given ◽  
General Method

Recently, there has been consistent growth in Android applications (apps). Under these circumstances, software maintenance for Android apps becomes an essential and important task. The core of software maintenance is to locate bugs in source files. Previous bug localization approaches mainly focus on open-source desktop software (e.g. Eclipse, Mozilla, GCC). Even though a few studies locate the bugs in the Android apps, they are dedicated to a special app named ZXing, without developing a general method to locate the bugs in Android apps by taking into account the unique characteristics of Android apps’ bug reports. Such characteristics include fewer number of historical bug reports, insufficient detailed description, etc. These characteristics hinder existing localization approaches from being directly delivered to Android apps, because lack of enough information degrades the performance of those localization approaches relying on historical bug reports. Commit messages include more informative data which can provide the details of reported bugs. Therefore, in this paper, we propose a novel information retrieval-based approach which utilizes commit messages to locate new bugs in Android apps. This approach not only considers the structured textual similarity between the given bug and the candidate source files, but also computes the unstructured textual similarities between the new bug and the commit messages linked to the corresponding source files. According to the experimental results on 10 popular open-source Android apps managed by GitHub, our approach outperforms the state-of-the-art bug localization methods that include BugLocator, BLUiR, and two-phase model.

scholarly journals Convolutional Neural Network for Classification of Android Applications Represented as Grayscale Images

2019 ◽  
Vol 8 (12S) ◽  
pp. 835-843
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
High Performance ◽  
Smart Phone ◽  
Convolution Neural Network ◽  
Android Malware ◽  
Android Applications ◽  
Conventional Solution ◽  
Grayscale Images

A rapid dissemination of Android operating system in smart phone market has resulted in an exponential growth of threats to mobile applications. Various studies have been carried out in academia and industry for the identification and classification of malicious applications using machine learning and deep learning algorithms. Convolution Neural Network is a deep learning technique which has gained popularity in speech and image recognition. The conventional solution for identifying Android malware needs learning based on pre-extracted features to preserve high performance for detecting Android malware. In order to reduce the efforts and domain expertise involved in hand-feature engineering, we have generated the grayscale images of AndroidManifest.xml and classes.dex files which are extracted from the Android package and applied Convolution Neural Network for classifying the images. The experiments are conducted on a recent dataset of 1747 malicious Android applications. The results indicate that classes.dex file gives better results as compared to the AndroidManifest.xml and also demonstrate that model performs better as the image become larger.

scholarly journals Fuzzy Integral-Based Multi-Classifiers Ensemble for Android Malware Classification

Mathematics ◽  
2021 ◽  
Vol 9 (22) ◽  
pp. 2880
Author(s):  
Altyeb Taha ◽  
Omar Barukab ◽  
Sharaf Malebary
Keyword(s):  
Difficult Problem ◽  
Third Party ◽  
Fuzzy Integral ◽  
User Privacy ◽  
Dynamic Nature ◽  
Android Malware ◽  
Android Apps ◽  
Multiple Classifiers ◽  
Malware Classification ◽  
Security Checks

One of the most commonly used operating systems for smartphones is Android. The open-source nature of the Android operating system and the ability to include third-party Android apps from various markets has led to potential threats to user privacy. Malware developers use sophisticated methods that are intentionally designed to bypass the security checks currently used in smartphones. This makes effective detection of Android malware apps a difficult problem and important issue. This paper proposes a novel fuzzy integral-based multi-classifier ensemble to improve the accuracy of Android malware classification. The proposed approach utilizes the Choquet fuzzy integral as an aggregation function for the purpose of combining and integrating the classification results of several classifiers such as XGBoost, Random Forest, Decision Tree, AdaBoost, and LightGBM. Moreover, the proposed approach utilizes an adaptive fuzzy measure to consider the dynamic nature of the data in each classifier and the consistency and coalescence between each possible subset of classifiers. This enables the proposed approach to aggregate the classification results from the multiple classifiers. The experimental results using the dataset, consisting of 9476 Android goodware apps and 5560 malware Android apps, show that the proposed approach for Android malware classification based on the Choquet fuzzy integral technique outperforms the single classifiers and achieves the highest accuracy of 95.08%.

scholarly journals A novel approach to big data analysis using deep belief network for the detection of android malware

2019 ◽  
Vol 16 (3) ◽  
pp. 1447
Author(s):  
Uma Narayanan ◽  
Varghese Paul ◽  
Shelbi Joseph
Keyword(s):  
Deep Learning ◽  
Big Data Analysis ◽  
Learning Systems ◽  
Android Security ◽  
Customer Data ◽  
Android Malware ◽  
Novel Approach ◽  
The Everyday ◽  
Dynamic Examination ◽  
Android Applications

Mobile and tablets are rapidly getting the chance to be basic device in the everyday life. Android has been the most well-known versatile working structure. Regardless, inferable from the open thought of Android, amount of malware is concealed in a broad number of kind applications in Android exhibits that really undermine Android security. Deep learning is another domain of AI explore that has expanded extending thought in artificial information. In this examination, we propose to relate the features from the static examination with features from the dynamic examination of Android applications and depict malware using Deep learning systems. What's more, besides distinguishing sensitive customer data sources is fundamental for security protection in portable applications. So we propose a Novel way to deal with overseeing tremendous information examination utilizing Deep learning for the affirmation of Android malware.

scholarly journals Analysis of Android Malware Using Data Replication Features Extracted by Machine Learning Tools

2019 ◽  
pp. 193-201
Author(s):  
Chandrashekhar Uppin ◽  
Gilbert George
Keyword(s):  
Machine Learning ◽  
Operating System ◽  
Dynamic Analysis ◽  
Identity Theft ◽  
Vital Role ◽  
Third Party ◽  
Learning Tools ◽  
Android Malware ◽  
Static And Dynamic Analysis ◽  
Using Data

In this era of technology, Smartphone plays a vital role in individual's life. Now-a-days, we tend to use smartphones for storing critical information like banking details, documents etc. as it makes it portable. Android is the most preferred type of operating system for smartphone as per consumer buying interest. But also, vulnerabilities are mainly targeted in case of android by malwares as android is the most vulnerable because of its third-party customization support, which results in identity theft, Denial of Services (DoS), Ransomware attacks etc. In this work, we present android malware called MysteryBot identification, static and dynamic analysis result. MysteryBot is a banking Trojan. Some recommended steps to make your android device safe from such kind of malwares infections are also explained in this paper.

Sign in / Sign up

Export Citation Format

Share Document