Phishing website detection using random forest algorithm
Not available
| Auteur principal: | |
|---|---|
| Autres auteurs: | |
| Format: | Master's thesis |
| Langue: | anglais |
| Publié: |
Universiti Teknologi Malaysia
2025
|
| Sujets: | |
| Accès en ligne: | https://utmik.utm.my/handle/123456789/40411 |
| Abstract | Abstract here |
| _version_ | 1854975066268237824 |
|---|---|
| author | Chiang, Jun Heng |
| author2 | Nor Azizah Ali, supervisor |
| author_facet | Nor Azizah Ali, supervisor Chiang, Jun Heng |
| author_sort | Chiang, Jun Heng |
| description | Not available |
| format | Master's thesis |
| id | utm-123456789-40411 |
| institution | Universiti Teknologi Malaysia |
| language | English |
| publishDate | 2025 |
| publisher | Universiti Teknologi Malaysia |
| record_format | dspace |
| record_pdf | Abstract |
| spelling | utm-123456789-404112025-08-20T23:21:20Z Phishing website detection using random forest algorithm Chiang, Jun Heng Nor Azizah Ali, supervisor Computing Not available The number of phishing techniques has increased, including the complexity. To carry out a well-designed phishing assault, phishers may use various techniques and strategies. Phishing victims, mostly online banking customers and payment service providers, are at risk of significant financial loss and a loss of trust in Internet-based services. There is a pressing need to create strategies to counteract phishing assaults to overcome these issues. Moreover, detecting a phishing website is a complex undertaking that needs much specialist knowledge and expertise. A variety of solutions to these issues have been suggested and created. However, some solutions have not yet been discovered. In this thesis, a Random Forest Algorithm to detect phishing websites is developed by training the dataset extracted from UCI Machine Learning Repository. Filter method will be used for feature selection to improve the model accuracy so that detect the phishing website can be detected accurately. The dataset with different variables will be produced and investigated by using Random Forest Algorithm with optimization. The model performance increased when undergoing the filter method as the dimension of the dataset was reduced. The detection accuracy results are 95.3573% for the origin dataset, 94.6639% for the dataset which the lower correlation with target variables is removed and 96.8698% which the higher correlation is removed. fahmimoksen UTM 142 p. Thesis (Sarjana Sains (Data Sains)) - Universiti Teknologi Malaysia, 2023 2025-03-06T09:57:41Z 2025-03-06T09:57:41Z 2023 Master's thesis https://utmik.utm.my/handle/123456789/40411 vital:152832 valet-20230820-104350 ENG Closed Access UTM Complete Unpublished Completion application/pdf Universiti Teknologi Malaysia |
| spellingShingle | Computing Chiang, Jun Heng Phishing website detection using random forest algorithm |
| thesis_level | Master |
| title | Phishing website detection using random forest algorithm |
| title_full | Phishing website detection using random forest algorithm |
| title_fullStr | Phishing website detection using random forest algorithm |
| title_full_unstemmed | Phishing website detection using random forest algorithm |
| title_short | Phishing website detection using random forest algorithm |
| title_sort | phishing website detection using random forest algorithm |
| topic | Computing |
| url | https://utmik.utm.my/handle/123456789/40411 |
| work_keys_str_mv | AT chiangjunheng phishingwebsitedetectionusingrandomforestalgorithm |