WIFI AUDIT FOR WIRELESS NETWORK USING AI GENERATED PASSWORDS

Abstract

HashCat and John the Ripper are most generally used password cracking tools employed by users to crack large set of passwords in shorter time span. Although these techniques can be used but to create, expand and to consider various datasets requires special training and experience, moreover they are time consuming and labor-intensive process. To address this issue, we use PassGAN to audit wireless networks. They are designed to use the machine learning algorithms to learn the characteristics and distribution pattern within a dataset and to derive a similar looking dataset instead of making use generated password rules. PassGAN employ a Generative Adversarial Network (GAN) which consists of a generator and discriminator instead of depending on manual analysis to automatically learn from the training dataset and to produce a similar password guesses list which closely matches the user to audit the network and for cracking the passwords of wireless networks.