cs.CRMay 19, 2025

Malware families discovery via Open-Set Recognition on Android manifest permissions

Authors: Filippo Leveni, Matteo Mistura, Francesco Iubatti, Carmine Giangregorio, Nicolò Pastore, Cesare Alippi, Giacomo Boracchi

Organizations: Department of Electronics, Information and Bioengineering. Politecnico di Milano - Milan, Italy · Cleafy S.p.A. - Milan, Italy · Faculty of Informatics. Università della Svizzera Italiana - Lugano, Switzerland

Abstract

Malware are malicious programs that are grouped into families based on their penetration technique, source code, and other characteristics. Classifying malware programs into their respective families is essential for building effective defenses against cyber threats. Machine learning models have a huge potential in malware detection on mobile devices, as malware families can be recognized by classifying permission data extracted from Android manifest files. Still, the malware classification task is challenging due to the high-dimensional nature of permission data and the limited availability of training samples. In particular, the steady emergence of new malware families makes it impossible to acquire a comprehensive training set covering all the malware classes. In this work, we present a malware classification system that, on top of classifying known malware, detects new ones. In particular, we combine an open-set recognition technique developed within the computer vision community, namely MaxLogit, with a tree-based Gradient Boosting classifier, which is particularly effective in classifying high-dimensional data. Our solution turns out to be very practical, as it can be seamlessly employed in a standard classification workflow, and efficient, as it adds minimal computational overhead. Experiments on public and proprietary datasets demonstrate the potential of our solution, which has been deployed in a business environment.

Figures & tables

Explore similar work

CardsList
  1. Automated Malware Family Classification using Weighted Hierarchical Ensembles of Large Language Models

    Apr 2, 2026Samita Bai, Hamed Jelodar, Tochukwu Emmanuel Nwankwo +4Malware ClassificationLanguage Model Ensembles

  2. MASCOT-Android: A Curated Dataset and Automated Collection Pipeline for Android Malware Source Code Specimens

    Jun 15, 2026Bojing Li, Duo Zhong, Prajna Bhandary +4Android Malware DetectionMalware Analysis

  3. Classifier-Dependent Benefits of Pseudo-Labeling for Semi-Supervised Android Malware Attribution

    Aug 26, 2026Md Rafid Islam, Zahid Hasan, Hafiz Abdur RahmanPseudo-LabelingMalware Classification