Prediction of android ransomware with deep learning model using hybrid cryptography.

Area of Science:

• Cybersecurity
• Mobile Security
• Artificial Intelligence

Background:

• Android ransomware is a growing threat to mobile user privacy and sensitive data.
• Existing detection methods lack accuracy and secure storage capabilities.
• There is a need for enhanced security measures against evolving Android malware.

Purpose of the Study:

• To develop a robust model for detecting Android ransomware.
• To implement a secure cloud storage solution for user data.
• To improve the accuracy and performance of malware detection systems.

Main Methods:

• Feature extraction from APK files using Squirrel Search Optimization.
• Classification of data as malicious or normal using an AlexNet deep learning model.
• Secured cloud storage via a hybrid cryptographic model (homomorphic Elliptic Curve Cryptography and Blowfish).

Main Results:

• The proposed deep learning model achieved 99.89% accuracy in malware detection.
• The system demonstrated superior performance compared to GNN (94.76%), CNN (95.76%), and Random Forest (96%).
• The hybrid cryptographic model ensured secure storage of non-malicious data in the cloud.

Conclusions:

• The proposed system effectively detects Android ransomware with high accuracy.
• The hybrid cryptographic approach provides secure data storage in the cloud.
• This research offers a significant advancement in mobile security against ransomware threats.