Password guessing set generation system and method

Abstract

The invention belongs to the technical field of information security, and discloses a password guessing set generation system and method. The method comprises the steps of: generating a probabilisticcontext-independent grammar based on personal information and a password database, dividing character strings in the probabilistic context-independent grammar into character strings suitable for or not suitable for training a long-term and short-term memory neural network according to classification rules, training a convergent long-term and short-term memory neural network model, generating a password segment and a probability corresponding to the password segment by using the convergent long-term and short-term memory neural network model, mapping the probabilities corresponding to the password segments into new probabilities, and sorting the password segments in a descending order according to the new probabilities, and generating passwords sorted in probability descending order. According to the method, the defects that a long-term and short-term memory neural network cannot identify the composition structure and semantic information in the password and is poor in interpretabilityare overcome; the defect of poor generalization capability of probabilistic context-independent grammar is overcome; and the problem that the probability of generating the password segment by the long-term and short-term memory neural network is low is solved.

Description

technical field [0001] The invention belongs to the technical field of information security, and in particular relates to a password guessing set generation system and method. Background technique [0002] At present, the closest existing technology: With the continuous development of the network and portable electronic devices, people's daily life is closely related to the network, and identity authentication has gradually become a basic means to ensure user information security. As a method of identity authentication, passwords are widely used because of their simplicity and ease of deployment, and have become one of the most important means of protecting user information security in the Internet world. Therefore, the security and usability of passwords have always been a matter of great concern. [0003] Password guessing algorithm is one of the important methods to study password security. Its basic idea is to generate a password guessing set for guessing user passwords...

AI Technical Summary

Problems solved by technology

The most primitive password guessing set generation method is to enumerate all eligible passwords, but because the entire password search space is extremely large, this method has poor feasibility and low efficiency

Then, people try to select frequently used words or numbers from the dictionary, and combine or slightly modify them as password guessing sets. These combination rules or modification rules are relatively simple and cannot accurately describe people's habit of generating passwords, and The probabilities of these passwords are not described, making guessing inefficient

Then, people use probabilistic models, such as probabilistic context-free grammar (PCFG for short) and Markov (Markov) model to generate password guessing sets, but the Markov model can only calculate the occurrences between characters before and after. The possibility of identifying the structure and semantic information of the password cannot be identified. Although the probabilistic context-free grammar can identify the structure and part of the semantic information in the password, it cannot generalize the password and can only combine the password segments that appear in the training set.

Recently, the method of using long-term short-term memory neural network or generative adversarial network to generate a password guessing set has appeared. It uses the advantage of neural network fitting to high-dimensional space to achieve better guessing results and has strong generalization ability. Similar to the Markov model, it cannot recognize the compositional structure and semantic information in passwords

[0004] To sum up, the problems existing in the existing technology are: the existing password guessing set generation technology cannot take into account the composition structure, semantic information and generalization ability of passwords, resulting in the generated password guessing set being unable to accurately describe the passwords generated by people. When using the password guessing set generated by existing technologies to guess passwords, it takes a lot of time and consumes a lot of computing resources to achieve an ideal guessing effect

[0006] Due to the different probability models used by existing password guessing set generation technologies, the probability of the generated passwords follows their own measurement standards. For example, for the same password, the probabilities given by different password guessing set generation technologies are different, sometimes even different. several orders of magnitude, so it is not possible to simply combine passwords generated by different models based on their probabilities and sort them in descending order of probability

Images