Detection of Permission Driven Malware in Android Using Deep Learning Techniques

Sirisha, P.; B, Kamala Priya; K, Aditya Kunal; Anuradha, T.

doi:10.1109/iceca.2019.8821811

Cited by 11 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The models are saved once it is trained with good accuracy. If an application has to classified as either benign or malware, the apk file of that particular application is decompiled and features are extracted from the application, then the saved model is loaded and provided with the feature set for prediction [11].…”

Section: Problem Descriptionmentioning

confidence: 99%

Deep Learning Based Static Analysis of Malwares in Android Applications

Nivedha¹,

K²,

Shibi³

et al. 2021

Advances in Parallel Computing Technologies and Applications

View full text Add to dashboard Cite

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.

show abstract

Section: Problem Descriptionmentioning

confidence: 99%

Deep Learning Based Static Analysis of Malwares in Android Applications

Nivedha¹,

K²,

Shibi³

et al. 2021

Advances in Parallel Computing Technologies and Applications

View full text Add to dashboard Cite

show abstract

“…Static Analysis analyzes compiled file without executing it and therefore can be used on small devices like smart phones which have constrained memory. Static analysis does not need any specific requirement to be fulfilled, does not need to set up any environment and therefore can give results in very less time [4]. This makes static analysis a good choice.…”

Section: Static Analysismentioning

confidence: 99%

“…Accuracy with DNN when all features are used is 94%. Sirisha P et al [4], used DNN and with 331 permission features, they were successful in detecting malware with the accuracy of more than 85%. Permission features were extracted using androguard package in python.…”

Section: Deep 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

“…However, users are generally uneducated about the risks of the permissions they can be asked to grant. They may grant permissions allowing malicious apps to exploit security breaches [2] and to monitor a mobile device without the user's consent [3]. These malwares can cause severe malfunction, steal sensitive personal information (e.g., banking information, passwords), corrupt files, display unwanted advertisement, and even lock the device unless a ransom is paid.…”

Section: Introductionmentioning

confidence: 99%

“…Malwares may go undiscovered if their signature is not identified in the database, and the databases must be continuously updated to stay relevant. Research literature on malware detection (e.g., [2,7,8]) includes advanced proposals using machine learning techniques to detect with a higher accuracy unknown Android malware embedded in APK files. Such work typically extracts features (e.g., permissions, and API calls in the code) from known benign apps and malware, then uses machine learning algorithms (e.g., decision tree, Random Forest) to uncover ways to detect malicious apps.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Android Anomaly Detection Using a Combination of Vulnerabilities Dataset

et al. 2021

View full text Add to dashboard Cite

As the leading mobile phone operating system, Android is an attractive target for malicious applications trying to exploit the system’s security vulnerabilities. Although several approaches have been proposed in the research literature for the detection of Android malwares, many of them suffer from issues such as small training datasets, there are few features (most studies are limited to permissions) that ultimately affect their performance. In order to address these issues, we propose an approach combining advanced machine learning techniques and Android vulnerabilities taken from the AndroVul dataset, which contains a novel combination of features for three different vulnerability levels, including dangerous permissions, code smells, and AndroBugs vulnerabilities. Our approach relies on that dataset to train Deep Learning (DL) and Support Vector Machine (SVM) models for the detection of Android malware. Our results show that both models are capable of detecting malware encoded in Android APK files with about 99% accuracy, which is better than the current state-of-the-art approaches.

show abstract

Detection of Permission Driven Malware in Android Using Deep Learning Techniques

Cited by 11 publications

References 6 publications

Deep Learning Based Static Analysis of Malwares in Android Applications

Deep Learning Based Static Analysis of Malwares in Android Applications

Analysis of Android Malware Detection Techniques in Deep Learning

Deep Learning Based Android Anomaly Detection Using a Combination of Vulnerabilities Dataset

Contact Info

Product

Resources

About