Technology Category
Machine Learning: Evaluation and AnalysisData Mining & Knowledge Management: Anomaly/Outlier DetectionNatural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
Benchmarking Machine Learning Models for IoT Malware Detection under Data Scarcity and Drift
🤖 AI Summary
This study systematically evaluates the performance of four lightweight supervised models—Random Forest, LightGBM, Logistic Regression, and Multilayer Perceptron—for malware detection on the IoT-23 dataset under the challenges of data scarcity and distribution shift. Emphasizing model sensitivity to training data volume and stability in temporally evolving threat landscapes, the findings reveal that tree-based models maintain high accuracy and generalization capability even with limited samples, though their performance degrades as malware diversity increases. These results underscore the necessity of dynamic adaptation mechanisms in real-world deployments. The work provides empirical evidence and design insights for robust malware detection in resource-constrained Internet of Things environments.
Technology Category
Application Category
📝 Abstract
The rapid expansion of the Internet of Things (IoT) in domains such as smart cities, transportation, and industrial systems has heightened the urgency of addressing their security vulnerabilities. IoT devices often operate under limited computational resources, lack robust physical safeguards, and are deployed in heterogeneous and dynamic networks, making them prime targets for cyberattacks and malware applications. Machine learning (ML) offers a promising approach to automated malware detection and classification, but practical deployment requires models that are both effective and lightweight. The goal of this study is to investigate the effectiveness of four supervised learning models (Random Forest, LightGBM, Logistic Regression, and a Multi-Layer Perceptron) for malware detection and classification using the IoT-23 dataset. We evaluate model performance in both binary and multiclass classification tasks, assess sensitivity to training data volume, and analyze temporal robustness to simulate deployment in evolving threat landscapes. Our results show that tree-based models achieve high accuracy and generalization, even with limited training data, while performance deteriorates over time as malware diversity increases. These findings underscore the importance of adaptive, resource-efficient ML models for securing IoT systems in real-world environments.
Problem
Research questions and friction points this paper is trying to address.
IoT malware detection
data scarcity
concept drift
machine learning benchmarking
temporal robustness
Innovation
Methods, ideas, or system contributions that make the work stand out.
IoT malware detection
data scarcity
concept drift
lightweight machine learning
temporal robustness
🔎 Similar Papers
No similar papers found.
