Hierarchical encryption method and system based on reinforcement learning

Abstract

The invention discloses a hierarchical encryption method based on reinforcement learning. The method comprises the following steps: dividing the current to-be-encrypted plaintext into multiple information units; determining encryption level of each information unit and a target encryption method corresponding to the encryption level according to a preset hierarchical encryption decision maker; andencrypting the current to-be-encrypted plaintext according to the target encryption method of each information unit. Through the above method disclosed by the invention, the current to-be-encrypted plaintext is divided into multiple information unit, the information unit is encrypted according to the target encryption method corresponding to the encryption level of each information unit, only theinformation unit is encrypted in the encryption process, and the problem that the transmission efficiency of the key is low since the same encryption way is used for all parts of the plaintext, the encryption key and the to-be-encrypted plaintext length are in positive correlation relation, the length of the key can be changed along the length of the to-be-encrypted plaintext if the to-be-encrypted plaintext is long, and the long key needs to occupy large transmission bandwidth in the transmission process is solved.

Description

technical field [0001] The invention relates to the technical field of reinforcement learning, in particular to a hierarchical encryption method and system based on reinforcement learning. Background technique [0002] In modern cryptography technology, in order to ensure the security of information transmission, the encryption method of fully encrypting the information in the plaintext to be encrypted is usually adopted. Taking the "one-time pad" encryption technology as an example, "one-time pad" refers to the information encryption process. Use a random key of the same length as the plaintext to be encrypted to perform an XOR operation to generate ciphertext. [0003] The inventor researched the existing information encryption process and found that, for encryption algorithms whose key length and plaintext length are positively correlated, since the same encryption method is used for all parts of the plaintext, if the plaintext to be encrypted is longer, the key’s The le...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the present invention provides a hierarchical encryption method and system based on reinforcement learning, which is used to solve the problems in the prior art when the plaintext to be encrypted is long due to the same encryption method for all parts of the plaintext. The length will also change with the length of the plaintext to be encrypted. A longer key needs to occupy a larger transmission bandwidth during the transmission process, resulting in low key transmission efficiency. The specific solution is as follows:

Images