Search 250 million research papers

Android Malware

Xuxian Jiang, Yajin Zhou · SpringerBriefs in computer science · 2013

Cited by 24

Android malware dataset

Singh · Zenodo (CERN European Organization for Nuclear Research) · 2026

Android Malware Analysis Dataset (2024–2025) 📌 Overview This dataset contains static analysis features extracted from 38 malware and 21 benign Android APKs downloaded from AndroZoo. The analysis is done by Androguard to extract the features and create a csv file.The samples are from January 2024 – March 2025, focusing on recent malware trends and obfuscation techniques.

Cited by 0Open access

Android malware detection

Aaditya Vikram Saravana Bhavan, Srujana Golla, Yuktha Poral et al. · 2024

There is an increasing trend to use mobile devices compared to other electronic devices in modern-day society. Android is currently the most popular mobile operating system. Many of the internet applications that were exclusively available on laptops and other similar electronic devices have migrated their products, accessibility, and applications to the mobile platform. More than 86.6% of the smartphones in the world are based on Android. The Android OS is very flexible and friendly. It also allows features such as open ecological mode, managing permissions in a coarse-grained manner, and being able to call third-party code. All these features induce the possibility of multiple ways of attacking the device. Due to this, Android devices are very vulnerable to malicious operations such as accessing user information by stealing, advertising, and so on. In this chapter, a detailed literature survey of various methods to tackle the problem of Android malware has been carried out.

Cited by 4

Android Malware Analysis

Md. Sadman Haque, Md Sakhawat Hossain, Robiul Awoul Robin et al. · Mendeley Data · 2026

The uploaded dataset (CIC-AndMal2017) contain curated information for Android malware analysis. The dataset is provided in CSV format and includes features selected for effective classification and detection of various malware families and benign applications. It is structured with clearly labeled columns for features and class labels, enabling straightforward use for research, analysis, and benchmarking in Android malware detection studies. This CSV dataset were generated from existing publicly available Android malware dataset. We extracted and organized the relevant features into CSV format to facilitate analysis and reproducibility.

Cited by 0Open access

Android Malware Analysis

Md. Sadman Haque, Md Sakhawat Hossain, Robiul Awoul Robin et al. · Mendeley Data · 2026

The uploaded dataset (CIC-AndMal2017) contain curated information for Android malware analysis. The dataset is provided in CSV format and includes features selected for effective classification and detection of various malware families and benign applications. It is structured with clearly labeled columns for features and class labels, enabling straightforward use for research, analysis, and benchmarking in Android malware detection studies. This CSV dataset were generated from existing publicly available Android malware dataset. We extracted and organized the relevant features into CSV format to facilitate analysis and reproducibility.

Cited by 0Open access

Android malware dataset

Singh · Zenodo (CERN European Organization for Nuclear Research) · 2026

Android Malware Analysis Dataset (2024–2025) 📌 Overview This dataset contains static analysis features extracted from 38 malware and 21 benign Android APKs downloaded from AndroZoo. The analysis is done by Androguard to extract the features and create a csv file.The samples are from January 2024 – March 2025, focusing on recent malware trends and obfuscation techniques.

Cited by 0Open access

Android Malware Detection

K. Kotteeswari, Amugadda Nitish Kumar, Nallagorla Ashok, Thadukala Sai Kumar · PhilPapers (PhilPapers Foundation) · 2025

With the rapid expansion of Android-based mobile applications, ensuring user security and privacy has become a growing concern. Android's open-source nature and widespread adoption have made it a prime target for malware developers. Traditional malware detection approaches, such as signature-based and heuristic techniques, are increasingly insufficient against sophisticated and evolving threats. This project aims to develop an intelligent Android malware detection system using machine learning techniques to identify malicious applications based on behavioral and static features extracted from APK files. The proposed system utilizes a comprehensive dataset consisting of both benign and malicious Android applications. Static analysis is performed by extracting features such as permissions, API calls, intents, and hardware components, without executing the code. These features are then preprocessed and used to train multiple machine learning models including Random Forest, Support Vector Machine (SVM), and Gradient Boosting Classifier. Among these, the Random Forest classifier demonstrated superior accuracy, precision, and recall in detecting malware, making it the most suitable model for deployment.

Cited by 0Open access

Android Malware Detection

N Gagan, Shivendra Kumar, M. Keerthana et al. · 2023

Since android smartphones are so popular, malware writers have found them to be lucrative targets, which poses a serious risk to user security and privacy. To address this problem, several malware detection strategies have been put out recently. In this review paper, we examine an efficient method for detecting malware on Android that makes use of machine learning techniques. Our method divides Android applications into benign and harmful categories using a combination of feature extraction methods and machine learning algorithms. Overall, our suggested method offers a dependable and efficient alternative for detecting Android malware, giving consumers a more dependable and safe environment for mobile computing.

Cited by 8

Android Malware Analysis

Trieu, Tho · Theseus (Ammattikorkeakoulujen) · 2021

The popularity of mobile devices leads to potential threats from hackers and intrusive techniques. Android platform is the most used operating system on mobile phones in the market share. Similar to Windows – most operating systems on computer and security problems, Android malware are increased significantly with different malicious activities and attacks.
\nThis thesis presents the technical overview of mobile malware and focuses on Android banking malware which is mostly created for target banks and financial institutions on mobile platforms. Through attacking methods, the Android operating system's problems in security aspects are discussed and compared with iOS.
\nIn addition, due to its popularity and frequency of regular appearances, some banking Trojans are analysed by reverse engineering. These Trojans are the common malware that hide as a third-party app, and have been infecting Android devices since 2017, studying these malware family gives a better understanding of how it works and finding preventive solutions.
\nAs a result of result of this thesis the key techniques and strategy of popular banking Trojans were analysed. Consequently, how to protect devices from online mobile banking platforms was discussed by identifying the tactics of banking Trojans.

Cited by 2Open access

Android Malware Detection

Prof.K.Shilpa Reddy · International Journal of Innovative Research in Advanced Engineering · 2026

Machine learning based detection system of Android malware and analysis of features which are static. The deigned system extracts non executable features such as permissions, intents, activities, and API calls from Android APK files. We analyze non-executable APK features and classify them using a Random Forest model deployed on a Flask server. Our Kotlin application interacts with this backend via REST APIs for real-time prediction. The Android application developed in Kotlin communicates with the backend using REST APIs to perform malware prediction in real time. Training of the model was done using datasets from Debrin, AndroZoo, and custom APK collections, accuracy of 95 Percentage, precision of 94 percentages, and recall of 93 percentages was achieved. The proposed solution provides an effective, scalable, and lightweight detection of malware approach, enhancing mobile security without relying on dynamic or runtime analysis.

Cited by 0Open access

Android Malware Analysis

Md. Sadman Haque, Md Sakhawat Hossain, Robiul Awoul Robin et al. · Mendeley Data · 2026

The uploaded dataset (CIC-AndMal2017) contain curated information for Android malware analysis. The dataset is provided in CSV format and includes features selected for effective classification and detection of various malware families and benign applications. It is structured with clearly labeled columns for features and class labels, enabling straightforward use for research, analysis, and benchmarking in Android malware detection studies. This CSV dataset were generated from existing publicly available Android malware dataset. We extracted and organized the relevant features into CSV format to facilitate analysis and reproducibility.

Cited by 0Open access

Android Malware Analysis

Haque, Md Sadman, Hossain, Md Sakhawat, Robin, Robiul Awoul et al. · Mendeley Data · 2026

The uploaded dataset (CIC-AndMal2017) contain curated information for Android malware analysis. The dataset is provided in CSV format and includes features selected for effective classification and detection of various malware families and benign applications. It is structured with clearly labeled columns for features and class labels, enabling straightforward use for research, analysis, and benchmarking in Android malware detection studies. This CSV dataset were generated from existing publicly available Android malware dataset. We extracted and organized the relevant features into CSV format to facilitate analysis and reproducibility.

Cited by 0Open access

Types of Android malware

Ковальчук, О. А., Kovalchuk, O. A. · ELARTU (Ternopil National Technical University) · 2024

Cited by 0

Android Dynamic Malware Analysis

Anunay Anand · International Journal for Research in Applied Science and Engineering Technology · 2025

In today’s mobile computing landscape, Android-based systems are highly prevalent and frequently targeted by malicious applications that exhibit anomalous behavior. Detecting such anomalies in real time is critical for ensuring system stability, user data privacy, and overall device security. This review paper explores the implementation and evaluation of unsupervised machine learning techniques for dynamic malware detection in Android applications. The focus is on models such as Isolation Forest, One-Class SVM, Local Outlier Factor, and Elliptic Envelope, which learn from normal process behavior to identify deviations without requiring labeled data. Among these, Isolation Forest demonstrates superior accuracy and efficiency, achieving up to 99% accuracy in detecting anomalous activity based on real-time process metrics like CPU usage, memory consumption, and disk operations. The system is designed to be lightweight, privacy-preserving, and suitable for deployment on individual devices without the need for external infrastructure. This paper also discusses the limitations of existing methods, presents a comparative analysis of model performance, and outlines potential future enhancements including deep learning integration, hybrid detection strategies, and cloud-based intelligence sharing. The findings support the feasibility and effectiveness of machine learning-driven anomaly detection as a proactive defense mechanism in modern Android environments.

Cited by 0Open access

"Multistage Android Malware Behaviour"

Sheikh Muhammad Zeeshan Javed · IEEE DataPort · 2025

"hash,tags,files_opened,files_dropped,files_copied,files_written,files_deleted,activities_started,permissions_checked,calls_highlighted,signals_hooked,services_opened,invokes,system_property_lookups,dns_lookups,http_conversations,verdict_labels "

Cited by 0Open access

Android Malware Family Labeling

Wang · Zenodo (CERN European Organization for Nuclear Research) · 2024

This repository includes VirusTotal scan reports of samples of two datasets used in the paper. (1) GPset-VT-Reports.zip: the first and second VT scans for the GPset samples. (2) 3rdset-VT-Reports.zip: the first and second VT scans for the 3rdset samples. (3)FusedApp-VT-Reports.zip: the VT scan for the fused (multi-family) samples. Each scan report is a JSON file generated by VirusTotal, including file metadata (e.g., hashes, size), certificate metadata (e.g., thumbprint), VirusTotal-specific data (e.g., submission time), and a list of detection labels assigned by various antivirus engines used to scan the file.

Cited by 0Open access

Android Malware Analysis Platform

Ben Andrews, Tae Oh, William Stackpole et al. · 2013

Abstracts—Malware for smartphones is a prominent threat to secu- rity, with Android leading the charge as a primary threat. To combat this, it is vital that the security field devote research into finding better methods of malware analysis and subsequently malware defense. As a result, initiative was taken to perform focused research on this subject in the form of an independent study. The purpose of the study is to develop a lab virtual environment for analyzing Android malware. The solution needs to be intuitive and centrally managed in order to be effective for a professor and their assistants. Work has begun on such a system, and the plan is to continue developing an environment until an adequate solution has been produced.

Cited by 0

Android malware classification method

Byeong Ho Kang, BooJoong Kang, Jung‐Tae Kim et al. · 2013

The number of Android malware is increasing with the growth of Android, so there needs to have a method to classify malware families. There are many classification methods proposed so far, but most of them are based on permission information such as the number of requested permissions and critical permissions. Since permission information cannot represent actual application behaviors and permissions are easily separated into several communicating applications, the permission based classification methods can result in false alarms. Opposed to these permission based methods, our classification method is based on applications' Bytecode that contains actual application behaviors. Each malicious application family may have some similar Bytecode and can be classified using this information. In this paper, we propose a method to classify malware families from known malware, as a pre-step of malware detection.

Cited by 35

Deep Android Malware Detection

Niall McLaughlin, Jesús Martínez del Rincón, BooJoong Kang et al. · Research Portal (Queen's University Belfast) · 2017

In this paper, we propose a novel android malware detection system that uses a deep convolutional neural network (CNN). Malware classification is performed based on static analysis of the raw opcode sequence from a disassembled program. Features indicative of malware are automatically learned by the network from the raw opcode sequence thus removing the need for hand-engineered malware features. The training pipeline of our proposed system is much simpler than existing n-gram based malware detection methods, as the network is trained end-to-end to jointly learn appropriate features and to perform classification, thus removing the need to explicitly enumerate millions of n-grams during training. The network design also allows the use of long n-gram like features, not computationally feasible with existing methods. Once trained, the network can be efficiently executed on a GPU, allowing a very large number of files to be scanned quickly.

Cited by 490Open access

Android Malware Genome Project

External Data Source · Department of Homeland Security, Information Marketplace for Policy and Analysis of Cyber-Risk & Trust (DHS-IMPACT) Repository · 2018

This project has managed to collect more than 1,200 malware samples that cover the majority of existing Android malware families, ranging from their debut in August 2010 to recent ones in October 2011. In addition, the samples are systematically characterized them from their various aspects, including their installation methods, activation mechanisms as well as the nature of carried malicious payloads. The characterization and a subsequent evolution-based study of representative families reveal that they are evolving rapidly to circumvent the detection from existing mobile anti-virus software. Based on the evaluation with four representative mobile security software, the experiments in November, 2011 show that the best case detects 79.6% of them while the worst case detects only 20.2% in the dataset. These results clearly call for the need to better develop next-generation anti-mobile-malware solution

Cited by 0Open access