Authors: Ahmed Bensaoud, Jugal Kalita

Published on: May 09, 2024

Impact Score: 8.2

Arxiv code: Arxiv:2405.05906

Summary

• What is new: A novel multi-task learning framework for malware classification that generates BMP and PNG images from malware features for detection.
• Why this is important: The global issue of malicious software detection needs a faster and more accurate solution.
• What the research proposes: A deep learning classifier using a novel multi-task learning framework for classifying malware images.
• Results: Achieved over 99.87% accuracy in detecting malware, demonstrating effectiveness against various obfuscation methods.

Technical Details

Technological frameworks used: Multi-task learning framework for malware image classification

Models used: Deep learning classifier with activation functions ReLU, LeakyReLU, PReLU, ELU

Data used: New dataset with 100,000 benign and malicious examples of PE, APK, Mach-o, and ELF files

Potential Impact

Cybersecurity market, antivirus software companies, businesses requiring malware protection

Want to implement this idea in a business?

We have generated a startup concept here: SafeGuardAI.