Multi-Class Classification Prediction Model for Password Strength Based on Deep Learning

Various indexes are being used today to evaluate the strength of passwords. In these indexes, a password is evaluated be high if it takes longer for an attacker predict it. Therefore, using such evaluation, there problem that leaked may reduce reliability index by increasing vulnerability attempts attack password. Hence, estimating frequency when considering important reducing vulnerability. This paper proposes evaluation model deep learning-based multi-class classification, which solves existing not considered during evaluation. Data preprocessing modeling critical improve performance this model. Additionally, since selecting and extracting feature values data also important, accurately estimates degree leakage through method proposed. To proposed model, experiment compares stored in database list was conducted. As result, correctly 99% 345 effectiveness verified.