Proactive password checking using neural network

Recently, passwords have been the common means of authentication method for computer security because of their ease of implementation and low maintenance cost. It is important to safeguard computer systems that the user selects good password. However, general users tend to choose easily guessable passwords. Most computer systems employ user password checking system to cope with this problem. In this paper, we propose a neural network that can classify easy-to-guess and hard-to-guess passwords for proactive password checking. The proposed neural network exploits password's linguistic information and successfully classify easy-to-guess and hard-to-guess password with over 99.9% accuracy. The proposed method in this paper can be extended to solve general classification problems with linguistic features.