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

DevFeed: [Malware families discovery via Open-Set Recognition on Android manifest permissions](<https://devfeed.tech/articles/malware-families-discovery-via-open-set-recognition-on-android-manifest-permissions-126869.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2505.12750>)

Author: Filippo Leveni, Matteo Mistura, Francesco Iubatti, Carmine Giangregorio, Nicol\\\`o Pastore, Cesare Alippi, Giacomo Boracchi

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Malware](<https://devfeed.tech/topics/malware.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>)

Tags: [android](<https://devfeed.tech/tags/android.md>), [classification](<https://devfeed.tech/tags/classification.md>), [computer-vision](<https://devfeed.tech/tags/computer-vision.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [detection](<https://devfeed.tech/tags/detection.md>), [discovery](<https://devfeed.tech/tags/discovery.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [malicious](<https://devfeed.tech/tags/malicious.md>), [malware](<https://devfeed.tech/tags/malware.md>), [malware-detection](<https://devfeed.tech/tags/malware-detection.md>), [manifest](<https://devfeed.tech/tags/manifest.md>), [mobile](<https://devfeed.tech/tags/mobile.md>), [mobile-devices](<https://devfeed.tech/tags/mobile-devices.md>), [open](<https://devfeed.tech/tags/open.md>), [penetration](<https://devfeed.tech/tags/penetration.md>), [permission](<https://devfeed.tech/tags/permission.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [recognition](<https://devfeed.tech/tags/recognition.md>), [set](<https://devfeed.tech/tags/set.md>)

## AI overview

The system classifies known Android malware families from manifest permissions and flags malware from previously unseen families, addressing the difficulty of building complete training sets as new families emerge. It combines MaxLogit open-set recognition with a tree-based Gradient Boosting classifier suited to high-dimensional permission data. The abstract says the approach fits into a standard classification workflow with minimal added computational overhead; experiments on public and proprietary datasets showed potential, and the system has been deployed in a business environment. The supplied text is an abstract, so it does not provide detailed performance results.

## Source excerpt

arXiv:2505.12750v2 Announce Type: replace 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.