Cyber Security Implementation Through Deep Learning Based Fraudulent URL Detection


  • K Suvarchala
  • Magham Esha Sree
  • V Shreya
  • P Sai Sharwani


Malicious URL, Cyber Security, Feature Engineering, KNN, Random Forest, CNN, Naïve Bayes, Decision Tree


A malicious URL, sometimes known as Spam, malicious ads, and drive-by vulnerabilities may all be found on a site that is malevolent. To find rogue URLs, you need to be quick. Researchers previously used blacklisting, regular expression searching and signature matching in their investigations. These strategies are worthless for discovering new malicious URLs or updated versions of previously problematic URLs. A machine learning-based approach may be developed to overcome this problem. For security objects such as URLs, this type of solution takes a lot of feature engineering and feature representation study. Furthermore, in order to support both versions of existing URLs and wholly new URLs, the resources required for feature engineering as well as feature representation must be updated on a regular basis. Deep learning, machine learning, and artificial intelligence (AI) systems have recently outperformed humans in a number of disciplines, and they have even exceeded human eyesight in certain computer vision applications. They can derive the optimum feature representation automatically, from raw data. Various machine learning techniques, including Decision Tree, KNN, SVM, Random Forest, Logistic Regression, Naive Bayes, RNN-LSTM, and others, benefit from character level embedding of raw URLs, CNN in the cyber security area.