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

2018/07/01 by Quan Le, Oisín Boydell, Brian Mac Namee +1 · 191 citations
Computer Science · #Advanced Malware Detection Techniques #Anomaly Detection Techniques and Applications #Artificial intelligence #Computer science #Computer security #Context (archaeology) #Data mining #Deep learning #Domain (mathematical analysis) #Domain knowledge #Feature (linguistics) #Identification (biology) #Machine learning #Malware #Network Security and Intrusion Detection #cs.AI #cs.CR #cs.LG

paper · pdf · doi:10.1016/j.diin.2018.04.024

published in Digital Investigation 26, S118-S126 (Elsevier BV)

openalex created_date 2018/03/29 · openalex publication_date 2018/07/01 · arxiv created 2018/07/22 · arxiv updated 2018/07/24 · openalex updated_date 2026/08/05

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.

Citations

• Challenges with Automation in Digital Forensic Investigations
• Adam: A Method for Stochastic Optimization
• Long Short-Term Memory
• Deep Learning in Neural Networks: An Overview
• ImageNet classification with deep convolutional neural networks
• Integration of Ether Unpacker into Ragpicker for plugin-based Malware Analysis and Identification
• Recent Trends in Deep Learning Based Natural Language Processing
• Microsoft Malware Classification Challenge
• Deep learning
• Squeeze-and-Excitation Networks