2020
DOI: 10.3390/sym13010035
|View full text |Cite
|
Sign up to set email alerts
|

Automatic Malicious Code Classification System through Static Analysis Using Machine Learning

Abstract: The development of information and communication technology (ICT) is making daily life more convenient by allowing access to information at anytime and anywhere and by improving the efficiency of organizations. Unfortunately, malicious code is also proliferating and becoming increasingly complex and sophisticated. In fact, even novices can now easily create it using hacking tools, which is causing it to increase and spread exponentially. It has become difficult for humans to respond to such a surge. As a resul… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
10
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
7

Relationship

0
7

Authors

Journals

citations
Cited by 11 publications
(11 citation statements)
references
References 10 publications
0
10
0
Order By: Relevance
“…In the learning process of the CAM method, the value that has the greatest influence on the normal/malignant classification is identified inversely to confirm the part of the input byte information that affects the classification. This process is illustrated in Figure 8 [15]. The validity of the proposed model (Malconv) was verified by comparing its accuracy with that of the learning model using byte block and file meta information as feature information by NVIDIA.…”
Section: Research On Nvidia's Dl-based Malware Detection Technologymentioning
confidence: 96%
See 2 more Smart Citations
“…In the learning process of the CAM method, the value that has the greatest influence on the normal/malignant classification is identified inversely to confirm the part of the input byte information that affects the classification. This process is illustrated in Figure 8 [15]. The validity of the proposed model (Malconv) was verified by comparing its accuracy with that of the learning model using byte block and file meta information as feature information by NVIDIA.…”
Section: Research On Nvidia's Dl-based Malware Detection Technologymentioning
confidence: 96%
“…As shown in Figure 7, NVIDIA conducted an experiment to detect malicious files by training a DL model with the byte information of files to detect malicious files in Windows executable files. As for the system configuration, the system for detecting malicious files consisted of preprocessing the byte information of executable files, training a DL model with the byte information, and classifying normal and malicious files [14,15]. To preprocess the input value for learning the DL model, the byte information (hexadecimal) of the executable file was converted into a form suitable for the input value of the learning algorithm.…”
Section: Research On Nvidia's Dl-based Malware Detection Technologymentioning
confidence: 99%
See 1 more Smart Citation
“…Source code can be retrieved from the APK file or Portable Executable (PE) file to perform the static analysis. In [70],…”
Section: Machinementioning
confidence: 99%
“…Thirty-two supervised ML algorithms were considered for most common vulnerabilities and identified that when the model used the J48 ML algorithm, 96% accuracy could be obtained in vulnerability detection. The model proposed in [123] discussed an automated mechanism to classify well-written and malicious code using a portable executable (PE) structure through static analysis and ML with an accuracy of 98.77%. The proposed methodology used RF, GB, DT, and CNN as ML models.…”
Section: Applying ML To Detect Source Code Vulnerabilitiesmentioning
confidence: 99%