Deep Q learning-based mitigation of man in the middle attack over secure sockets layer websites
Abstract
To ensure the security of web applications and to reduce the constant risk of increasing cybercrime, basic security principles like integrity, confidentiality and availability should not be omitted. Even though Transport Layer Security/Secure Socket Layer (TLS/SSL) authentication protocols are developed to shield websites from intruders, these protocols also have their fair share of problems. Incorrect authentication process of websites can give birth to notorious attack like Man in The Middle attack, which is widespread in HTTPS websites. In MITM attack, the violator basically positions himself in a communication channel between user and website either to eavesdrop or impersonate the communicating party to achieve malicious goals. Initially, the MITM attack is defined as a binary machine learning problem. Deep Q learning is utilized to build the MITM attack classification model. Thereafter, training process is applied on 60% of the obtained dataset. Remaining 40% dataset is used for testing purpose. The experimental results indicate that the proposed technique performs significantly better than the existing machine learning technique-based MITM prediction techniques for SSL/TLS-based websites.
