Android Malware Detection Method Based on Permission Complement and API Calls

Jun, Yang; Tang, Jinjin; Yan, Ran; Xiang, Tao

doi:10.1049/cje.2020.00.217

Cited by 8 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, based on the feature selection algorithm described in literature [14], the objective is to generate a smaller feature set that boosts classification performance compared to the full set. This algorithm provides the selected feature set to the detection model for training and testing, repeating this process until the detection model reaches its peak accuracy.…”

Section: 3extraction Of Valid Permission Feature Vectormentioning

confidence: 99%

Android malware detection based on multi-feature fusion and deep learning

Wang,

Xiong,

Wang

et al. 2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

In recent years, the ubiquity of mobile devices has witnessed a concomitant surge in malware attacks, with Android platforms emerging as predominant targets. The inherent open-source architecture of the Android operating system inadvertently paves the way for the proliferation of malevolent applications. Conventional malware detection methodologies, which predominantly hinge on manual feature extraction and juxtaposition against feature repositories, are notably resource-draining. Furthermore, an over-reliance on singular features often obfuscates the demarcation between benign and malevolent applications. To address this lacuna, this study propounds an innovative Android malicious code detection paradigm, amalgamating multifarious features with the prowess of deep learning. By decompiling APK (Android application package), we extract three static features: Opcode (operation code), API (application program interface) call, and Permission (permission). We use the N-Gram method to process the operation code to improve the extraction efficiency, filter out effective permissions to improve the classification accuracy, and select APIs related to permissions to increase the logic between features. After encoding, we input them into DNN for classification. Experiments on a dataset containing 8008 applications show that using multi-features and deep learning networks can significantly improve the accuracy of malware detection, verifying the superiority of this method in detecting malicious code.

show abstract

Section: 3extraction Of Valid Permission Feature Vectormentioning

confidence: 99%

Android malware detection based on multi-feature fusion and deep learning

Wang,

Xiong,

Wang

et al. 2024

Fourth International Conference on Sensors and Information Technology (ICSI 2024)

View full text Add to dashboard Cite

show abstract

“…In the paper by Tang et al, 1 the authors introduce a critical threat in autonomous vehicle security with the Android operating system: Android malware. Then, this article presents an Android malware classification method centered around multi‐feature fusion and deep learning architecture, as well as uses different experiments to evaluate the proposed method.…”

Section: Papers In This Special Sectionmentioning

confidence: 99%

Safety and security of autonomous vehicles

Kumari,

Xiong,

Khoukhi

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

“…Khariwal & Arora mengusulkan deteksi malware pada android berdasarkan permission dengan menggunakan beberapa algoritma machine learning seperti SVM, Naive Bayes dan Random Forest [4]. Hasil yang didapat Random Forest memiliki akurasi paling tinggi dalam deteksi malware android berdasarkan permission [5]. Pada studi kasus klasifikasi debitur berdasarkan kualitas kredit menyatakan bahwa klasifikasi Random Forest merupakan metode klasifikasi yang memiliki tingkat akurasi paling tinggi untuk klasifikasi kualitas kredit yaitu mencapai 98,16% disusul Naïve Bayes 95,93% [6].…”

Section: Pendahuluanunclassified

Prediksi Kategori Serangan Siber dengan Algoritma Klasifikasi Random Forest Menggunakan Rapidminer

Rabbani,

Diana

2023

SMATIKA

View full text Add to dashboard Cite

Serangan siber menjadi ancaman serius bagi organisasi atau lembaga yang menggunakan jaringan komputer dalam operasinya, salah satunya Dinas Komunikasi dan Informatika Kota Palembang. Oleh karena itu, penelitian ini bertujuan untuk mengimplementasikan algoritma klasifikasi Random Forest pada platform Rapidminer untuk memprediksi kategori serangan siber pada Dinas Komunikasi dan Informatika Kota Palembang. Data yang digunakan dalam penelitian ini adalah data serangan siber dari perangkat firewall selama periode tertentu. Data tersebut diproses menggunakan Rapidminer dengan algoritma Random Forest untuk memprediksi kategori serangan siber. Hasil penelitian ini memberikan nilai akurasi yang tinggi sehingga memungkinkan pihak yang bertanggung jawab untuk segera mengambil tindakan pencegahan atau response terhadap serangan siber yang merugikan Dinas Komunikasi dan Informatika Kota Palembang. Hasil yang didapatkan dari evaluasi menggunakan confusion matrix dan accuracy score, didapatkan nilai akurasi 99.84% dan nilai out of bag error 0.16.

show abstract

Android Malware Detection Method Based on Permission Complement and API Calls

Cited by 8 publications

References 27 publications

Android malware detection based on multi-feature fusion and deep learning

Android malware detection based on multi-feature fusion and deep learning

Safety and security of autonomous vehicles

Prediksi Kategori Serangan Siber dengan Algoritma Klasifikasi Random Forest Menggunakan Rapidminer

Contact Info

Product

Resources

About