Android Malware Analysis: A Survey Paper

Barsiya, Tarang Kumar; Gyanchandani, Manasi; Wadhwani, Rajesh

doi:10.5121/ijcacs.2016.1105

Cited by 6 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Note that we have removed some application files from which any manifest file or permission information could not be extracted in decompilation process. This is because the reverse engineering tool 6 we used fails in some cases where it may require to find and install mobile OS specific framework files in order to properly decode application program files 7 . The number of samples before and after the decompressing in our selected datasets are given in Table 3.…”

Section: Performance Evaluation 41 Datasetsmentioning

confidence: 99%

“…The main difference between the static and dynamic approaches is the necessity of running application on the device [3,4,12,42]. The hybrid analysis is a combination of static and dynamic methods, and it creates a framework to perform both of the analyses [2,7,31,49]. In hybrid approach, the static analysis is performed at first without executing the application.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adapting Text Categorization for Manifest based Android Malware Detection

Çoban¹,

Özel²

2019

csci

View full text Add to dashboard Cite

Malware is a shorthand of malicious software that are created with the intent of damaging hardware systems, stealing data, and causing a mess to make money, protest something, or even make war between governments. Malware is often spread by downloading some applications for your hardware from some download platforms. It is highly probable to face with a malware while you try to load some applications for your smart phones nowadays. Therefore it is very important that some tools are needed to detect malware before loading them to the hardware systems. There are mainly three different approaches to detect malware: i) static, ii) dynamic, and iii) hybrid. Static approach analyzes the suspicious program without executing it. Dynamic approach, on the other hand, executes the program in a controlled environment and obtains information from operating system during runtime. Hybrid approach, as its name implies, is the combination of these two approaches. Although static approach may seem to have some disadvantages, it is highly preferred because of its lower cost. In this paper, our aim is to develop a static malware detection system by using text categorization techniques. To reach our goal, we apply text mining techniques like feature extraction by using bag-of-words, n-grams, etc. from manifest content of suspicious programs, then apply text classification methods to detect malware. Our experimental results revealed that our approach is capable of detecting malicious applications with an accuracy between 94.0% and 99.3%.

show abstract

Section: Performance Evaluation 41 Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adapting Text Categorization for Manifest based Android Malware Detection

Çoban¹,

Özel²

2019

csci

View full text Add to dashboard Cite

show abstract

“…Oleh beberapa pengembang, malware dirancang untuk melakukan kerusakan pada suatu sistem yang diinfeksi, aktivitas yang dilakukan diantaranya menggangu kinerja komputer, sistem operasi, mencuri data atau informasi rahasia secara ilegal [7] [8] [9]. Sehingga dengan begitu dibutuhkan adanya sistem yang dapat mendeteksi atau pun mencegah serangan malware [10].…”

Section: Pendahuluanunclassified

Analisis Klasterisasi Malware: Evaluasi Data Training Dalam Proses Klasifikasi Malware

Akbi

Rosyadi

2018

eltikom

View full text Add to dashboard Cite

Data latih merupakan salah satu bagian penting pada proses klasifikasi. Terutama jika data tersebut digunakan untuk membuat sistem pendeteksi malware. Penelitian ini melakukan perbandingan data latih yang dihasilkan dari dua penelitian yang telah dilakukan sebelumnya, data yang digunakan pada kedua penelitian tersebut merupakan data malware android berdasarkan frekuensi system call sejumlah 600 data. Penelitian pertama melakukan klasifikasi dan menghasilkan 4 jenis malware, sedangkan penelitian kedua melakukan klastering dan menghasilkan 8 klaster. Dari kedua penelitian tersebut, peneliti melakukan evaluasi data latih dari masing - masing penelitian untuk mendapatkan hasil data latih yang lebih akurat, dengan menggunakan data uji sejumlah 50, peneliti melakukan evaluasi dan uji coba dengan menggunakan algoritme kNN. Hasil yang didapatkan, penggunaan data latih berdasarkan hasil klastering pada proses klasifikasi lebih direkomendasikan, hasil Error Prediction penelitian pertama: 0,995 sedangkan pada penelitian kedua: 0,998. Hasil Recall dan akurasi menggunakan metode cross validation, penelitian pertama, Recall: 0,665 akurasi: 0,66, penelitian kedua, Recall: 0,893 akurasi: 0,89, sedangkan Hasil Recall dan akurasi menggunakan metode precentage split, penelitian pertama, Recall: 0,657 akurasi: 0,65, penelitian kedua, Recall: 0,798 akurasi: 0,79. Berdasarkan hasil pengujian, proses klastering yang menggunakan data frekuensi system call malware menghasilkan data latih yang lebih akurat dibandingkan dengan data latih yang dihasilkan dengan menggunakan suatu situs penamaan malware.

show abstract

One-dimensional convolutional neural networks for Android malware detection

Hasegawa

Iyatomi

2018

2018 IEEE 14th International Colloquium on Signal Processing &Amp; Its Applications (CSPA)

View full text Add to dashboard Cite

Android Malware Analysis: A Survey Paper

Cited by 6 publications

References 1 publication

Adapting Text Categorization for Manifest based Android Malware Detection

Adapting Text Categorization for Manifest based Android Malware Detection

Analisis Klasterisasi Malware: Evaluasi Data Training Dalam Proses Klasifikasi Malware

One-dimensional convolutional neural networks for Android malware detection

Contact Info

Product

Resources

About