Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Re-Evaluating Android Malware Detection: Tabular Features, Vision Models, and Ensembles

View through CrossRef
Static, machine learning-based malware detection is widely used in Android security products, where even small increases in false-positive rates can impose significant burdens on analysts and cause unacceptable disruptions for end users. Both tabular features and image-based representations have been explored for Android malware detection. However, existing public benchmark datasets do not provide paired tabular and image representations for the same samples, limiting direct comparisons between tabular models and vision-based models. This work investigates whether carefully engineered, domain-specific tabular features can match or surpass the performance of state-of-the-art deep vision models under strict false-positive-rate constraints, and whether ensemble approaches justify their additional complexity. To enable this analysis, we construct a large corpus of Android applications with paired static representations and evaluate six popular machine learning models on the exact same samples: two tabular models using EMBER features, two tabular models using extended EMBER features, and two vision-based models using malware images. Our results show that a LightGBM model trained on extended EMBER features outperforms all other evaluated models, as well as a state-of-the-art approach trained on a much larger dataset. Furthermore, we develop an ensemble model combining both tabular and vision-based detectors, which yields a modest performance improvement but at the cost of substantial additional computational and engineering overhead.
Title: Re-Evaluating Android Malware Detection: Tabular Features, Vision Models, and Ensembles
Description:
Static, machine learning-based malware detection is widely used in Android security products, where even small increases in false-positive rates can impose significant burdens on analysts and cause unacceptable disruptions for end users.
Both tabular features and image-based representations have been explored for Android malware detection.
However, existing public benchmark datasets do not provide paired tabular and image representations for the same samples, limiting direct comparisons between tabular models and vision-based models.
This work investigates whether carefully engineered, domain-specific tabular features can match or surpass the performance of state-of-the-art deep vision models under strict false-positive-rate constraints, and whether ensemble approaches justify their additional complexity.
To enable this analysis, we construct a large corpus of Android applications with paired static representations and evaluate six popular machine learning models on the exact same samples: two tabular models using EMBER features, two tabular models using extended EMBER features, and two vision-based models using malware images.
Our results show that a LightGBM model trained on extended EMBER features outperforms all other evaluated models, as well as a state-of-the-art approach trained on a much larger dataset.
Furthermore, we develop an ensemble model combining both tabular and vision-based detectors, which yields a modest performance improvement but at the cost of substantial additional computational and engineering overhead.

Related Results

Dynamic Features for Robust Malware Detection: A Systematic Review, Taxonomy, and Practical Analysis Framework
Dynamic Features for Robust Malware Detection: A Systematic Review, Taxonomy, and Practical Analysis Framework
The need to mitigate malware attacks cannot be overemphasized, as they pose serious threats to the critical information assets in cyberspace. Understanding and utilizing appropriat...
Android Malware Detection Techniques: A Literature Review
Android Malware Detection Techniques: A Literature Review
Objective: This paper provides the basics of Android malware, its evolution and tools and techniques for malware analysis. Its main aim is to present a review of the literature on ...
PELATIHAN MEMBUAT APLIKASI ANDROID DENGAN ANDROID STUDIO PADA SMP NEGERI 1 TINGGI RAJA
PELATIHAN MEMBUAT APLIKASI ANDROID DENGAN ANDROID STUDIO PADA SMP NEGERI 1 TINGGI RAJA
Abstract: The community service activity entitled "Training on Making Android Applications with Android Studio at junior high school 1 Tinggi Raja" aims to train existing students ...
Image-Based Malware Multiclass Classification Using Vision Transformer Architecture
Image-Based Malware Multiclass Classification Using Vision Transformer Architecture
Perkembangan malware yang semakin canggih telah menjadi ancaman serius bagi keamanan siber global, mengakibatkan kerugian finansial yang signifikan. Metode deteksi tradisional sepe...
Analisis dan Deteksi Malware dengan Metode Hybrid Analysis Menggunakan Framework MOBSF
Analisis dan Deteksi Malware dengan Metode Hybrid Analysis Menggunakan Framework MOBSF
Abstract - The increase in the popularity of smartphones is followed by an increase in the number of users each year. In this case, smartphones with the Android platform are still ...
The rise of obfuscated Android malware and impacts on detection methods
The rise of obfuscated Android malware and impacts on detection methods
The various application markets are facing an exponential growth of Android malware. Every day, thousands of new Android malware applications emerge. Android malware hackers adopt ...
Malware Behaviour Visualization
Malware Behaviour Visualization
The number of unique malware variants released each year is on the rise. Researchers may often need to use manual static and dynamic analysis to study new malware samples. Manual a...
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
The pandemic Covid-19 currently demands teachers to be able to use technology in teaching and learning process. But in reality there are still many teachers who have not been able ...

Back to Top