Skripsi
KLASIFIKASI MALICIOUS URL PADA FILE BERBASIS HOST-BASED FEATURE EXTRACTION MENGGUNAKAN METODE LSTM
Dangers on the internet can endanger users by malicious actors who attack them covertly. These attacks include phishing, malware, spyware, and ransomware. One very effective cyberattack tool carried out by attackers is using URLs. A URL (Uniform Resource Locator) is an address used to find the location of a file on the internet. This makes URLs used as one method for carrying out cyberattacks called Malicious URLs. Malicious URLs or dangerous sites on the internet contain a lot of content in the form of spam and phishing, which are used to launch attacks. In this study, a URL dataset was generated with URL features in the form of DNS records from URLs that will be used as data in conducting LSTM. And produced a visualization of the LSTM results data using epoch 100, namely benign URLs and malicious URLs. And conducting an analysis of the visualization results of LSTM using the validation test obtained with the results in this study, resulting in model validation by training the URL dataset on machine learning and applying Hypeparameter tuning so that the performance results of each test ratio are benign (0) precision 85%, Recall 97%, F1-Score 91%, and malicious cluster (1) precision 96%, Recall 92%, F1-score 94%, and the accuracy results of the model used are with a value of 94.6%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2507005399 | T182703 | T1827032025 | Central Library (Reference) | Available but not for loan - Not for Loan |