Deep learning at the shallow end: Malware classification for non-domain experts

TL;DR

This paper introduces a deep learning method for malware classification that eliminates the need for expert knowledge and manual feature extraction, focusing on a data-driven approach to identify complex patterns.

Contribution

It proposes a novel deep learning framework that automates malware classification without relying on predefined signatures or expert feature engineering.

Findings

Achieves accurate malware classification without domain expertise

Reduces reliance on manual signature-based detection methods

Demonstrates effectiveness of deep learning in complex pattern recognition

Abstract

Current malware detection and classification approaches generally rely on time consuming and knowledge intensive processes to extract patterns (signatures) and behaviors from malware, which are then used for identification. Moreover, these signatures are often limited to local, contiguous sequences within the data whilst ignoring their context in relation to each other and throughout the malware file as a whole. We present a Deep Learning based malware classification approach that requires no expert domain knowledge and is based on a purely data driven approach for complex pattern and feature identification.