INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Phishing attacks are a prevalent security threat, and detecting and preventing such attacks is crucial to safeguarding sensitive information. By performing a phishing attack the attacker can get hold of the victim’s personal details including login credentials, and credit card details, and perform some fraudulent activities. To address this issue, our proposed method makes use of machine learning techniques and uses some classification algorithms, such as K-nearest neighbor, decision trees, Random Forest and Ada Boost to identify phishing URLs. For this we use a dataset that consists of 38,625 data of which 16,252 data are legitimate and are taken from alexa.com and 22,373 data are phishing taken from phishtank.com.
The data pre-processing is performed on the data by applying techniques such as under-sampling and over-sampling, and as a part of feature extraction 12 features are selected and the model is trained on these data, then the model is tested using the test data. Finally, we evaluate the performance of each algorithm using performance metrics such as accuracy, precision, f1 score, and recall.
After evaluating the algorithms, we save the best-performing model in a pickle file. Our results indicate that the Random Forest classifier achieved the highest accuracy, with a score of 96.56%. Using the Flask framework, we developed a web application, where the user can check the legitimacy of the URL.
Once the user enters the URL in the search bar provided, then our model will predict whether the URL is legitimate or a phishing attempt, and if it is a phishing URL, a warning message will be displayed to the user. This approach will help prevent users from falling victim to phishing attacks and safeguard their sensitive information.
Keywords:
Phishing, cybersecurity, data mining, encryption, Random Forest Classifier, Flask Framework.
Cite Article:
"FLASK WEBSITE FOR DETECTING PHISHING WEBSITES USING MACHINE LEARNING", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 4, page no.c446-c451, April-2023, Available :http://www.ijnrd.org/papers/IJNRD2304258.pdf
Downloads:
000118752
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn