ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Alam, Md Tanvirul, Piplai, Aritran, Rastogi, Nidhi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908476472557568
author Alam, Md Tanvirul
Piplai, Aritran
Rastogi, Nidhi
author_facet Alam, Md Tanvirul
Piplai, Aritran
Rastogi, Nidhi
contents Machine learning models are commonly used for malware classification; however, they suffer from performance degradation over time due to concept drift. Adapting these models to changing data distributions requires frequent updates, which rely on costly ground truth annotations. While active learning can reduce the annotation burden, leveraging unlabeled data through semi-supervised learning remains a relatively underexplored approach in the context of malware detection. In this research, we introduce \texttt{ADAPT}, a novel pseudo-labeling semi-supervised algorithm for addressing concept drift. Our model-agnostic method can be applied to various machine learning models, including neural networks and tree-based algorithms. We conduct extensive experiments on five diverse malware detection datasets spanning Android, Windows, and PDF domains. The results demonstrate that our method consistently outperforms baseline models and competitive benchmarks. This work paves the way for more effective adaptation of machine learning models to concept drift in malware detection.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection
Alam, Md Tanvirul
Piplai, Aritran
Rastogi, Nidhi
Machine Learning
Cryptography and Security
Machine learning models are commonly used for malware classification; however, they suffer from performance degradation over time due to concept drift. Adapting these models to changing data distributions requires frequent updates, which rely on costly ground truth annotations. While active learning can reduce the annotation burden, leveraging unlabeled data through semi-supervised learning remains a relatively underexplored approach in the context of malware detection. In this research, we introduce \texttt{ADAPT}, a novel pseudo-labeling semi-supervised algorithm for addressing concept drift. Our model-agnostic method can be applied to various machine learning models, including neural networks and tree-based algorithms. We conduct extensive experiments on five diverse malware detection datasets spanning Android, Windows, and PDF domains. The results demonstrate that our method consistently outperforms baseline models and competitive benchmarks. This work paves the way for more effective adaptation of machine learning models to concept drift in malware detection.
title ADAPT: A Pseudo-labeling Approach to Combat Concept Drift in Malware Detection
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2507.08597