Security and Communication Networks

Malware Analysis and Vulnerability Detection Using Machine Learning


Publishing date
01 Dec 2020
Status
Closed
Submission deadline
17 Jul 2020

Lead Editor

1King Saud University, Riyadh, Saudi Arabia

2National University of Sciences and Technology, Islamabad, Pakistan

3Zhongnan University of Economics and Law, Wuhan, China

This issue is now closed for submissions.

Malware Analysis and Vulnerability Detection Using Machine Learning

This issue is now closed for submissions.

Description

Continuing to grow in volume and complexity, malware is today one of the major threats faced by the digital world. The intent of malware is to cause damage to a computer or network and often involves performing an illegal or unsanctioned activity that can be used to conduct espionage or receive economic gains. Malware attacks have even started to affect embedded computational platforms such as Internet of Things (IoT) devices, medical equipment, and environmental and industrial control systems. Most modern malware types are complex, and many possess the ability to change code as well as the behavior in order to avoid detection. Instead of relying on traditional defense mechanisms, typically comprising the use of signature-based techniques, there is a need to have a broader spectrum of techniques to deal with the diverse nature of malware.

The variants of malware families share typical behavioral patterns that can be obtained either statically or dynamically. Static analysis typically refers to the techniques that analyze the contents of malicious files without executing them, whereas dynamic analysis considers the behavioral aspects of malicious files while executing tasks such as information flow tracking, function call monitoring, and dynamic binary instrumentation. Machine learning techniques can exploit such static and behavioral artefacts to model the evolving structure of modern malware, therefore enabling the detection of more complex malware attacks that cannot be easily detected by traditional signature-based methods. Nonreliance on signatures makes machine-learning-based methods more effective for newly released (zero-day) malware. Moreover, the feature extraction and representation process can further be improved by using deep learning algorithms that can implicitly perform feature engineering.

This Special Issue aims to attract top-quality original research and review articles covering the latest ideas, techniques, and empirical findings related to malware analysis and machine learning.

Potential topics include but are not limited to the following:

  • Machine learning and/or artificial intelligence in malware analysis
  • Malware analysis for IoT, resource constrained devices, and mobile platforms
  • Software vulnerability prediction with machine learning and/or artificial intelligence
  • Advances in the detection and prevention of zero-day malware attacks, advanced persistent threats, and cyber deception using machine learning and/or artificial intelligence
  • Latest trends in vulnerability exploitation, malware design,
  • and machine learning and/or artificial intelligence

Articles

  • Special Issue
  • - Volume 2020
  • - Article ID 8841544
  • - Research Article

MD-MinerP: Interaction Profiling Bipartite Graph Mining for Malware-Control Domain Detection

Tzung-Han Jeng | Yi-Ming Chen | ... | Chuan-Chiang Huang
  • Special Issue
  • - Volume 2020
  • - Article ID 8810708
  • - Research Article

Automatic Analysis Architecture of IoT Malware Samples

Javier Carrillo-Mondejar | Juan Manuel Castelo Gomez | ... | José Luis Martínez
  • Special Issue
  • - Volume 2020
  • - Article ID 6724513
  • - Research Article

SLAM: A Malware Detection Method Based on Sliding Local Attention Mechanism

Jun Chen | Shize Guo | ... | Zhisong Pan
  • Special Issue
  • - Volume 2020
  • - Article ID 8810817
  • - Research Article

GFD: A Weighted Heterogeneous Graph Embedding Based Approach for Fraud Detection in Mobile Advertising

Jinlong Hu | Tenghui Li | ... | Shoubin Dong
  • Special Issue
  • - Volume 2020
  • - Article ID 8840058
  • - Research Article

An Efficient and Effective Approach for Flooding Attack Detection in Optical Burst Switching Networks

Bandar Almaslukh
  • Special Issue
  • - Volume 2020
  • - Article ID 8826038
  • - Research Article

BLATTA: Early Exploit Detection on Network Traffic with Recurrent Neural Networks

Baskoro A. Pratomo | Pete Burnap | George Theodorakopoulos
  • Special Issue
  • - Volume 2020
  • - Article ID 8850550
  • - Research Article

HYBRID-CNN: An Efficient Scheme for Abnormal Flow Detection in the SDN-Based Smart Grid

Pengpeng Ding | Jinguo Li | ... | Yuyao Guan
  • Special Issue
  • - Volume 2020
  • - Article ID 1924140
  • - Research Article

Group Recommender Systems Based on Members’ Preference for Trusted Social Networks

Xiangshi Wang | Lei Su | ... | Liping Wu
  • Special Issue
  • - Volume 2020
  • - Article ID 7913061
  • - Research Article

Design and Analysis of a Novel Chaos-Based Image Encryption Algorithm via Switch Control Mechanism

Shenyong Xiao | ZhiJun Yu | YaShuang Deng
  • Special Issue
  • - Volume 2020
  • - Article ID 7501894
  • - Research Article

Using a Subtractive Center Behavioral Model to Detect Malware

Ömer Aslan | Refik Samet | Ömer Özgür Tanrıöver
Security and Communication Networks
Publishing Collaboration
More info
Wiley Hindawi logo
 Journal metrics
See full report
Acceptance rate10%
Submission to final decision143 days
Acceptance to publication35 days
CiteScore2.600
Journal Citation Indicator-
Impact Factor-
 Submit Check your manuscript for errors before submitting

Article of the Year Award: Impactful research contributions of 2022, as selected by our Chief Editors. Discover the winning articles.