Experience Replay: A value-based deep reinforcement approach for Malicious URL Detection in the Tor Browser

Finding malicious URLs in Tor is vital for preserving network security and privacy. Subsequently, Tor affords anonymity by routing traffic over a sequence of relays, it's frequently used for both legitimate and illegitimate reasons. Malicious URLs can lead to various threats, including phishing, malware distribution and illegal activities. Malicious URLs can lead users to websites hosting malware, which can compromise their devices and steal sensitive information. This article explores the discovery of malicious URLs through the ML and DL concepts. By utilizing the techniques such as Correlation-based Feature Selection, Chi-Square Test, Principal Component Analysis and Linear Discriminant Analysis, key features which are contributing to URL detection can be identified. Implementation of KNN, K Means, Random Forest, DQN and DDQN algorithms offers intuitions into how malicious URLs are recognized and alleviates possible cyber threats efficiently. The objective of this work includes, the idea of applying the deep reinforcement learning methods in which can pave the way to surge the accuracy of detection of the URL. It also stretches an idea for employing the deep reinforcement learning techniques for the chosen dataset.