A Novel DL Approach to PE Malware Detection: Exploring Glove Vectorization, MCC_RCNN and Feature Fusion

Yuzhou Lin

doi:10.47297/taposatWSP2633-456903.20210205

PDF
Export
Share
Collection
Album

A Novel DL Approach to PE Malware Detection: Exploring Glove Vectorization, MCC_RCNN and Feature Fusion

Volume 2, Issue 5

Views: 0 Downloads: 6

A Novel DL Approach to PE Malware Detection: Exploring Glove Vectorization, MCC_RCNN and Feature Fusion
A Novel DL Approach to PE Malware Detection: Exploring Glove Vectorization, MCC_RCNN and Feature Fusion
Beijing Jiaotong University
Vol. 2, Issue 5, Pages: 15-34(2021)
Published： 2021 ，
DOI：10.47297/taposatWSP2633-456903.20210205
Accepted：

Scan QR Code

YUZHOU LIN. (2021). A Novel DL Approach to PE Malware Detection: Exploring Glove Vectorization, MCC_RCNN and Feature Fusion. Theory and Practice of Science and Technology, 2(5), 15-34..
DOI：

YUZHOU LIN. (2021). A Novel DL Approach to PE Malware Detection: Exploring Glove Vectorization, MCC_RCNN and Feature Fusion. Theory and Practice of Science and Technology, 2(5), 15-34.. DOI： 10.47297/taposatWSP2633-456903.20210205.

摘要

Abstract

In recent years

malware becomes more threatening. Concerning the increasing malware variants

there comes Machine Learning (ML)-based and Deep Learning (DL)-based approaches for heuristic detection. Nevertheless

the prediction accuracy of both needs to be improved. In response to the above is-sues in the PE malware domain

we propose the DL-based approaches for de-tection and use static-based features fed up into models. The contributions are as follows: we recapitulate existing malware detection methods. That is

we propose a vectorized representation model of the malware instruction layer and semantic layer based on Glove. We implement a neural network model called MCC_RCNN (Malware Detection and Recurrent Convolutional Neural Net-work)

comprising of the combination with CNN and RNN. Moreover

we pro-vide a description of feature fusion in static behavior levels. With the numerical results generated from several comparative experiments towards evaluating the Glove-based vectorization

MCC_RCNN-based classification methodology and feature fusion stages

our proposed classification methods can obtain a higher prediction accuracy than the other baseline methods.

关键词

Keywords

Deep learningMalware DetectionGlove VectorizationFeature Fusion

references

Chang Yiheng, Ma Zhaorui, Li Xia, Gong Daofu. “A Survey of Network Security Situation Awareness” [J]. Cyberspace Security, 2019, 10 (12): 88-93.[2] Zhang Boqing, Sun Shuyang. “Outlook for China’s cybersecurity development in 2019” [J]. Cyberspace Security, 2019, 10 (01): 36-41.[3] The World Economic Forum released the “Global Risk Report 2018” [EB / OL]. Http://www.fortunechina.com/busine ss / c / 2018-01 / 29 / content_301395.htm? Id = mail. [ 2018-01-29].[4] Rising China Cybersecurity Report 2019 [EB / OL]. Http://it.rising.com.cn/dongtai/19692.html. [2020-01-15].[5] 360 Analysis report of ransom virus outbreak in the first half of 2019 [EB / OL]. Https://www.360.cn/n/10828.html. [2019-07-30].[6] Apple Issues iPhone FaceTime Security Warning [EB / OL]. Https://www.forbes.com/site s / gordon kelly / 2019/01/29 / apple-ios-12-1-3-release-iphone -xs-max-xr-problem-facetime-problem-video-calls-audio-calls / # 2b786a684020. [2019-01-29].[7] The hacker organization Silence expanded the scope of the attack to the world [EB / OL]. Https://www.360.cn/n/10969.html. [2019-08-23].[8] The Toyota company in Vietnam was attacked, and it is suspected that the Sea Lotus or-ganization launched [EB / OL] to support the local auto industry.[9] Xiao Junyong, Meng Dahua. “Research on the Rule of Law of Information Network Security from the Perspective of Overall National Security Concept” [J]. Cyberspace Security, 2019, 10 (05): 7-11 + 17.[10]Minar M R, Naher J. “Recent Advances in Deep Learning: An Overview” [J]. 2018.[11]Yuan Z, Lu Y, Wang Z, et al. “Droid-Sec: deep learning in android malware detection.” [J]. Acm Sigcomm Computer Communication Review, 2014, 44 (4): 371-72.[12]Saxe J, Berlin K. Deep neural network based malware detection using two dimensional bi-nary program features [C] // 2015 10th International Conference on Malicious and Un-wanted Software (MALWARE). IEEE, 2015: 11-20.[13]Fan Y, Ye Y, Chen L. “Malicious sequential pattern mining for automatic malware detection” [J]. Expert Systems with Application, 2016, 52 (Jun.): 16-25.[14]Pascanu R, Stokes J W, Sanossian H, et al. Malware classification with recurrent net-works[C]// IEEE International Conference on Acoustics,Speech and Signal Processing. IEEE, 2015:1916-20.[15]Pezeshki, Mohammad. Sequence Modeling using Gated Recurrent Neural Networks. Computer Science, 2015.[16]Sundermeyer, Martin & Schlüter, Ralf & Ney, Hermann. LSTM Neural Networks for Language Modeling. 2012: 601-08.[17]Cui Z, Xue F, Cai X, et al. “Detection of Malicious Code Variants Based on Deep Learning” [J]. IEEE Transactions on Industrial Informatics, 2018: 1-1.[18]Zhang Haoyi. “WebShell detection method based on semantic analysis and neural network” [J]. Cyberspace Security, 2019, 10 (02): 17-23.[19]Dolev S, Tzachar N. Malware signature builder and detection for executable code [C]. Patent Application, 2010: 1-5.[20] Bilar, Daniel. “Opcodes as predictor for malware” [J]. International Journal of Electronic Security and Digital Forensics, 2007, 1 (2): 156.[21]Hochreiter, S, Schmidhuber, J. “Long Short-Term Memory” [J]. Neural Computation, 9 (8): 1735-80.[22]Gers F A, Schmidhuber J. Recurrent nets that time and count [C]. International joint con-ference on netural network, Budapest, 2000: 189-94.[23]Cho K, Van Merrienboer B, Gulcehre C, et al. “Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation” [J]. Empirical methods in natural language processing, 2014: 1724-34.[24]Dauphin Y N, Fan A, Auli M, et al. “Language Modeling with Gated Convolutional Net-works”[J]. arXiv preprint axXiv:1612.08083, 2016.[25]Agarap A F. “Towards Building an Intelligent Anti-Malware System: A Deep Learning Approach using Support Vector Machine (SVM) for Malware Classification”[J]. 2017.[26]Dauphin Y N, Fan A, Auli M, et al. Language Modeling with Gated Convolutional Net-works[J]. arXiv preprint axXiv:1612.08083, 2016.[27]Ullah K R, Xiaosong Z, Rajesh K. “Analysis of ResNet and GoogleNet models for malware detection”[J]. Journal of Computer Virology & Hacking Techniques, 2018, 14(1):1-9.[28]Kim H J. “Image-Based Malware Classification Using Convolutional Neural Network”[J]. Advances in Computer Science and Ubiquitous Computing(CSA-CUTE 17). 2017, 474(1):1352-57.

Alert me when the article has been cited

Submit

Research on Image Content Retrieval Technology Based on Visual Feature Extraction

Application of deep learning in visual detection in intelligent manufacturing environment

A Novel Method for Real-time Multi-modal Digital Human Control

Research on Renewable Energy Generation Prediction Based on Artificial Intelligence

Stock Price Forecasting Based on the MDT-CNN-CBAM-GRU Model: An Empirical Study

Related Author

Chengwei Bai

Xuefei Xiong

Guanyu Li Chengdu No. 7 High School, Gaoxin

Suxuan Yang School of Electrical and Electronic Engineering, Nanyang Technological University