Ensemble Malware Classification Using Neural Networks

Wyrwinski, Piotr; Dutkiewicz, Jakub; Jędrzejek, Czesław

doi:10.1007/978-3-030-59000-0_10

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, attackers exploit access to hardware flaws and conceal the harmful code on the end-user devices. Anti-malware applications are unable to conduct significant analysis on Android hardware components [19]. The attacker's ability to employ various stealth techniques such as key permutation, dynamic loading, native code execution, code encryption, and java reflection is used in the malware that is utilized to escape from anti-malware software [20][21][22].…”

Section: General Overviewmentioning

confidence: 99%

“…Sometimes, getting static features requires additional initial steps to decompile APK files in order to build the feature sets to be exploited in the classifying process [28,40]. As well, CNN improved the performance of ML classifiers by employing CNN as a feature extractor from assembly and binaries malware files [19,63]. CNN not only handled images for classifying malware files but also used analyzing words of static features for malware [24].…”

Section: Cnn Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Malware Classification Approaches Utilizing Binary and Text Embedding of Permissions

Zyout

Shatnawi

Najadat

2022

Preprint

View full text Add to dashboard Cite

The development of mobile applications is rapidly increasing with the advances in smartphone technology. These applications are intended to assist mobile users in accomplishing various daily tasks including e-commerce and online services. Many mobile applications were also developed to attack smartphone users. Hence, new challenges have been found such as the difficulty to distinguish between benign and malicious malware categories.In this paper, two approaches for classifying malware applications are presented, including Conv1d (Conventional one dimension) and LSTM (Long short Time Memory). The proposed approaches have modeled and solved the malware classification problem using the natural language processing method. Two encoding techniques, binary and text encoding, were conducted on android permissions as a preprocessing phase. In addition, two other classifiers, the Support Vector Machine (SVM) and K-Nearest Neighbor(KNN) were also reported. The two main approaches were evaluated on well-known dataset, the CICMalDroid2020. The Conv1d-approach and LSTM-approach using text encoding achieved the best classification, i.e., high precision and accuracy (98.16\%, 97.72\% and 96.63\%, 96.69\%, respectively). The Conv1d-approach on binary classification has outperformed the LSTM-approach model when compared with Mal-prem and datasets. The Conv1d-approach achieved the best performance, with 99.3\%,99.80\%, 98.90\%, and 98.95\% of accuracy.

show abstract