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

Quan Le, Oisín Boydell, Brian Mac Namee, Mark Scanlon

2018-07-22Malware Classification General Classification Classification Malware Detection

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.

Results

Task	Dataset	Metric	Value	Model
Malware Classification	Microsoft Malware Classification Challenge	Accuracy (5-fold)	98.2	CNN BiLSTM - Reb Sampl
Malware Classification	Microsoft Malware Classification Challenge	F1 score (5-fold)	96.05	CNN BiLSTM - Reb Sampl

Related Papers

Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17 Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation2025-07-16 Safeguarding Federated Learning-based Road Condition Classification2025-07-16 AI-Enhanced Pediatric Pneumonia Detection: A CNN-Based Approach Using Data Augmentation and Generative Adversarial Networks (GANs)2025-07-13 Fuzzy Classification Aggregation for a Continuum of Agents2025-07-06 Hybrid-View Attention for csPCa Classification in TRUS2025-07-04 Devising a solution to the problems of Cancer awareness in Telangana2025-06-26 A Semi-supervised Scalable Unified Framework for E-commerce Query Classification2025-06-26