DESIGN AND IMPLEMENTATION OF ARTIFICIAL DATASET MALWARE USING SELF-SUPERVISED LEARNING METHOD
Various types of attacks (malware) are currently carried out by infiltrating interconnected systems by exploiting vulnerabilities found in various devices and software applications. the development of a malware defense system needs to be developed to fight malware attacks and detect the potential fo...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/58856 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Various types of attacks (malware) are currently carried out by infiltrating interconnected systems by exploiting vulnerabilities found in various devices and software applications. the development of a malware defense system needs to be developed to fight malware attacks and detect the potential for new malware to emerge. This study aims to detect malware to avoid attacks on the devices used. BERT self-supervised learning is used as a method to detect malware types. The dataset uses GAN and EMBER data to detect two types of malware, namely Mallicious and Benign. The results show that the use of BERT is able to detect up to 85% accuracy and provides a fairly good performance. |
|---|