Detection of Android Malware in the Internet of Things through the K-Nearest Neighbor Algorithm.

Area of Science:

• Cybersecurity
• Machine Learning
• Internet of Things (IoT)

Background:

• Android devices are increasingly prevalent in IoT ecosystems.
• Growing Android malware poses significant threats to system security and user privacy.
• Predicting and mitigating these threats is crucial for secure IoT operation.

Purpose of the Study:

• To develop and evaluate a machine learning-based framework for predicting Android malware in IoT devices.
• To enhance the security of consumer devices by identifying and blocking malicious applications.
• To minimize energy utilization through efficient malware detection.

Main Methods:

• An internet-based framework utilizing static analysis for feature extraction.
• Comparison of multiple machine learning algorithms including Naive Bayes, Decision Tree, Support Vector Machine, and K-Nearest Neighbor (KNN).
• K-Nearest Neighbor (KNN) was selected as the proposed model for its performance.

Main Results:

• The K-Nearest Neighbor (KNN) model achieved the highest prediction rate of 93% for Android malware.
• KNN demonstrated strong performance with 93% accuracy, 95% precision, 90% recall, and 92% F1-score.
• The system effectively identified malicious applications among over 10,000 tested Android apps.

Conclusions:

• The proposed machine learning framework, particularly the KNN model, is effective in predicting Android malware on IoT devices.
• The system successfully aids in blocking malicious apps, thereby protecting cloud data and user privacy.
• This approach offers an energy-efficient solution for securing consumer IoT devices against evolving Android threats.