Computer Science
a year ago

Phishing Sites Beware: AI Outperforms Humans in Detecting Malicious Websites

Prediction of Phishing Sites in Network using Naive Bayes compared over Random Forest with improved Accuracy
Pendyala Raja Yaswanth, V. Nagaraju

Paper Summary

The goal of the research was to improve the accuracy of predicting phishing sites in a network. The researchers used Naive Bayes and Random Forest classifiers with a dataset from Kaggle. Naive Bayes had a higher accuracy rate of 95.58% compared to Random Forest's 94.675%. This means Naive Bayes is better at predicting new phishing sites in a network.

Related papers

Theme background image
Computer Science
8 years ago

Optimal classifier achieves highest recognition rates for classification tasks.

Imbalanced Data
Dimensionality Reduction
Learning with Noisy Labels
Theme background image
Chemistry
8 years ago

New classifier accurately identifies components in complex systems using masked data.

Chemometrics
Dimensionality Reduction
Multicollinearity
Theme background image
Computer Science
8 years ago

New method accurately predicts pattern classification risks, improving decision-making processes.

Learning with Noisy Labels
Neural Networks
Regularization Methods