Detection of clone scammers in Android markets using IoT‐based edge computing

Ullah, Farhan; Naeem, Hamad; Naeem, Muhammad Rashid; Jabbar, Sohail; Khalid, Shehazad; Al‐Turjman, Fadi; Abuarqoub, Abdelrahman

doi:10.1002/ett.3791

Cited by 4 publications

(9 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this reason, distinguishing repackaged or fake applications and analyze the behaviors of variants is also an essential task. From the collected primary studies, six studies apply deep learning techniques to detect variants [16,77,108,109,163,164]. By unpacking a software package and then repackaging it after a purposeful modification of original codes, a fake application with malicious intention is created to misguide mobile users to install it in application markets.…”

Section: Results Analysismentioning

confidence: 99%

“…By unpacking a software package and then repackaging it after a purposeful modification of original codes, a fake application with malicious intention is created to misguide mobile users to install it in application markets. In order to locate mobile counterfeit applications in application markets, Ullah et al [163] and Karunanayake et al [77] propose DL-based Fake app detectors to prevent the publishing of fake apps in app stores. Except that, there are two primary studies on the detection of variants of malware families [108,164].…”

Section: Results Analysismentioning

confidence: 99%

“…Java code: Classes.dex could be decompiled into a higher-level format, .java files. Java codes can be viewed as text information to be processed, so encoders in NLP can be used to extract feature information from java codes [163,193]. Except that, Zhang et al [202] apply a bag-of-words-based code clone approach, SourcererCC [141], to perform a similarity analysis on java source codes and then built a similarity feature vector.…”

Section: Static Analysismentioning

confidence: 99%

“…In fact, one-hot encoding is the simplest method of text encoding but one of the disadvantages is the high dimensional problem we discussed before. In addition, some researchers employ discrete representation approaches like Bag of Words (BOW), Term Frequency-Inverse Document Frequency (TF-IDF) and N-Gram to select words [11,127,132,159,163,165,188,193], but these methods still suffer from the problem of data sparsity and high dimensionality [173]. Therefore, many primary studies further investigate the effectiveness of pre-trained word embedding models, such as Continuous Word2vec [19,25,46,76,171,202,212] and GloVe [76], to learn the non-contextual representation from the extracted semantic features of Android APKs.…”

Section: Hybrid Analysismentioning

confidence: 99%

See 3 more Smart Citations

Deep Learning for Android Malware Defenses: a Systematic Literature Review

Liu,

Tantithamthavorn,

et al. 2021

Preprint

View full text Add to dashboard Cite

Malicious applications (especially in the Android platform) are a serious threat to developers and end-users. Many research efforts have hence been devoted to developing effective approaches to defend Android malware. However, with the explosive growth of Android malware and the continuous advancement of malicious evasion technologies like obfuscation and reflection, android malware defenses based on manual rules or traditional machine learning may not be effective due to limited apriori knowledge. In recent years, a dominant research field of deep learning (DL) with the powerful feature abstraction ability has demonstrated a compelling and promising performance in various fields, like Nature Language processing and image processing. To this end, employing deep learning techniques to thwart the attack of Android malware has recently gained considerable research attention. Yet, there exists no systematic literature review that focuses on deep learning approaches for Android Malware defenses. In this paper, we conducted a systematic literature review to search and analyze how deep learning approaches have been applied in the context of malware defenses in the Android environment. As a result, a total of 104 studies were identified over the period 2014-2020. The results of our investigation show that even though most of these studies still mainly consider DL-based on Android malware detection, 35 primary studies (33.7%) design the defenses approaches based on other scenarios. This review also describes research trends, research focuses, challenges, and future research directions in DL-based Android malware defenses.CCS Concepts: • Security and privacy → Malware and its mitigation; Software security engineering;• General and reference → Surveys and overviews.

show abstract

Section: Results Analysismentioning

confidence: 99%

Section: Results Analysismentioning

confidence: 99%

Section: Static Analysismentioning

confidence: 99%

Section: Hybrid Analysismentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Android Malware Defenses: a Systematic Literature Review

Liu,

Tantithamthavorn,

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The authors have also used an artificial bee colony attack detection which helps to recognize the eavesdropper. In Reference 41, the authors suggested a clone detection system for the IoT devices for Android. They have used a deep learning model to predict clones in Android applications.…”

Section: Related Workmentioning

confidence: 99%

Analysis on homomorphic technique for data security in fog computing

Murugesan

Balamurali

Al‐Turjman³

et al. 2020

Trans Emerging Tel Tech

Self Cite

View full text Add to dashboard Cite

The fog computing model has given new trends of networking with different types of devices providing services at the end‐user point. It inherits most advanced features of cloud computing with localization rather than centralization like a cloud. It builds a platform for the Internet of things of different standards. Similar to the cloud, it is prone to privacy and security threat while sharing resources and services at the network edge. When the request for support is with more sensitive data, for example, as in business or research area, then fog devices face many potential threats resulting in leakage of data. The existing cloud environment provides data sharing service to the legal requestor in a highly secured manner using cryptographic encryption techniques. The uploaded data undergoes encryption and decryption, at the sending and receiving end only on providing the private key. Even more, security can be achieved by further computation on encrypted data. As an extension to fog computing, the data communication between fog nodes‐fog nodes and fog node‐cloud center is done with encryption/decryption for ensuring confidentiality. Homomorphic encryption is a cryptographic technique which allows performing computations on encrypted data without decryption so that the original message need not be disclosed to intermediates (servers) who are the only service provider and not a data user. Our work is motivated by the flaw of security issues in fog computing platforms, which involve heterogeneous devices.

show abstract