RPNDroid: Android Malware Detection using Ranked Permissions and Network Traffic

Upadhayay, Madan; Sharma, Ashutosh; Garg, Gourav; Arora, Anshul

doi:10.1109/worlds451998.2021.9513992

Cited by 17 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Windowed sequence statistical features: Maintaining packet time intervals and packet lengths in separate windows for outbound and inbound traffic, extracting statistical features for each window such as mean, standard deviation, maximum, and minimum values. Additionally, employing a Markov transition matrix to capture relationships between adjacent packets [8] .…”

Section: Flow-level Featuresmentioning

confidence: 99%

Data mining of encrypted network traffic for adult content and gambling Android applications

Wang,

Ning,

Cheng

et al. 2024

Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024)

View full text Add to dashboard Cite

With the advancement of mobile computing technology, there has been a rampant increase in mobile-based pornography, gambling, and scams in the recent past, leading to deception and loss of personal property, resulting in serious societal and legal issues. Therefore, we decided to investigate adult and gambling applications, discover, and analyze their encrypted traffic characteristics. We crawled a massive database of malicious domains and automatically downloaded data, including 687 gambling applications and 334 adult Android applications This paper presents an empirical research study based on the real traffic of mobile pornography and gambling applications, delving into data mining and analyzing their traffic characteristics at the packet and session flow levels. As these applications involve the dissemination of adult content and scams, running them on an emulator and collecting traffic files does not constitute a violation of privacy. Through quantitative analysis of the encrypted traffic features of such applications, this research aims to provide assistance in the identification and classification of adult and gambling applications and related tasks.

show abstract

Section: Flow-level Featuresmentioning

confidence: 99%

Data mining of encrypted network traffic for adult content and gambling Android applications

Wang,

Ning,

Cheng

et al. 2024

Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024)

View full text Add to dashboard Cite

show abstract

“…Permissions are a major source of malware infection [11], [12] [13], [14]. Studies that use permissions for malware detection generate attribute feature vectors from the AndroidManifest.xml file where a one is assigned if the permission is present; otherwise, a zero is assigned [15], [16][17]- [19]. Other studies use text classification techniques such as Term Frequency-Inverse Document Frequency [6].…”

Section: Static Analysismentioning

confidence: 99%

BarkDroid: Android Malware Detection Using Bark Frequency Cepstral Coefficients

Tarwireyi

Terzoli

Adigun

2022

Indonesian J. of Inf. Syst.

View full text Add to dashboard Cite

Since their inaugural releases in 2007, Google’s Android and Apple’s iOS have grown to dominate the mobile OS market share. Currently, they jointly possess over 99% of the global market share with Android being the leading mobile Operating System of choice worldwide, controlling close to 70% of the market share. Mobile devices have enabled the exponential growth of a plethora of mobile applications that play key roles in enabling many use cases that are pivotal in our daily lives. On the other hand, access to a large pool of potential end users is available to both legitimate and nefarious applications, thus making mobile devices a burgeoning target of malicious applications. Current malware detection solutions rely on tedious, time-consuming, knowledge-based, and manual processes to identify malware. This paper presents BarkDroid, a novel Android malware detection technique that uses the low-level Bark Frequency Cepstral Coefficients audio features to detect malware. The results obtained outperform results obtained using other features on the same datasets. BarkDroid achieved 97.9% accuracy, 98.5% precision, an F1 score of 98.6%, and shorter execution times.

show abstract

“…They found an imbalanced data problem, that was, the most network traffic generated by malwares was normal and only a small proportion of the network traffic was malicious [31]. Upadhayay et al [32] proposed a model that detected and mined the network traffic patterns of each APP and built a classification model that took the traffic patterns as input. Fallah et al [33] proposed a malware detection method based on LSTM and network traffic analysis, which distinguished malwares and benignwares, and detected unseen malware families.…”

Section: Network Traffic Analysis-based Detectionmentioning

confidence: 99%

“…Upadhayay et al. [32] proposed a model that detected and mined the network traffic patterns of each APP and built a classification model that took the traffic patterns as input. Fallah et al.…”

Section: Related Workmentioning

confidence: 99%

Android malware detection via efficient application programming interface call sequences extraction and machine learning classifiers

Wang

Zhao

et al. 2022

IET Software

View full text Add to dashboard Cite

Malware detection is an important task for the ecosystem of mobile applications (APPs), especially for the Android ecosystem, and is vital to guarantee the user experience of Android APPs. There have been some exiting methods trying to solve the problem of malware detection, but the methods suffer from several defects, such as high time complexity and mediocre accuracy, which seriously decrease the practicability of existing methods. To solve these problems, in this study, we propose a novel Android malware detection framework, where we contribute an efficient Application Programming Interface (API) call sequences extraction algorithm and an investigation of different types of classifiers. In API call sequences extraction, we propose an algorithm for transforming the function call graph from a multigraph into a directed simple graph, which successfully avoids the unnecessary repetitive path searching. We also propose a pruning search, which further reduces the number of paths to be searched. Our algorithm greatly reduces the time complexity. We generate the transition matrix as classification features and investigate three types of machine learning classifiers to complete the malware detection task. The experiments are performed on real-world Android Packages (APKs), and the results demonstrate that our method significantly reduces the running time and produces high detection accuracy. K E Y W O R D SAndroid (operating system), computational complexity, pattern classification, software quality, software reliability | INTRODUCTIONMobile applications (APPs) have been indispensable to daily lives, and the Android and iOS are the two most widely used mobile platforms [1]. There are a bunch of mobile APP markets and people expect to download high-quality APPs from those markets. But the mobile markets probably involve the malicious APPs (i.e. malware), especially the Android APP markets [2]. Malwares contain the malicious codes that are likely to affect the integrity, confidentiality or functionality of APPs [3]. Malwares usually have seven characteristics, which are the forced installation, difficult uninstallation, browser hijacking, advertisement pop-up, malicious user information collection, malicious uninstallation and malicious bundling [4]. Cyber-criminals may use malwares to attack individuals and organisations, which can disrupt operating systems, invade computer networks, steal confidential data, collect personal information, hijack data, or encrypt sensitive data [5]. Such malicious behaviours seriously compromise user information and system security. Therefore, malware detection is an inevitable task.Researchers have developed several solutions to detect malwares for Android and there are three mainstream methodologies, that is, dynamic analysis, network traffic analysis andThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial...

show abstract

RPNDroid: Android Malware Detection using Ranked Permissions and Network Traffic

Cited by 17 publications

References 26 publications

Data mining of encrypted network traffic for adult content and gambling Android applications

Data mining of encrypted network traffic for adult content and gambling Android applications

BarkDroid: Android Malware Detection Using Bark Frequency Cepstral Coefficients

Android malware detection via efficient application programming interface call sequences extraction and machine learning classifiers

Contact Info

Product

Resources

About