Stanford Technology Ventures Program
In this paper, the authors apply multilayer feed-forward neural networks to phishing email detection and evaluate the effectiveness of this approach. The authors design the feature set, process the phishing dataset, and implement the Neural Network (NN) systems. They then use cross validation to evaluate the performance of NNs with different numbers of hidden units and activation functions. They also compare the performance of NNs with other major machine learning algorithms. From the statistical analysis, they conclude that NNs with an appropriate number of hidden units can achieve satisfactory accuracy even when the training examples are scarce.