Novel continuous variable quantum key distribution method based on machine learning

Abstract

The invention discloses a novel continuous variable quantum key distribution method based on machine learning. The method comprises: a sending end preparing a modulation coherent state with a known mark and sends the modulation coherent state to a receiving end; the receiving end obtaining a measurement result; extracting features and dividing a training set and a test set; using the training setto train a classifier to obtain a training classifier, and using the test set to test and obtain a quantum classifier; the sending end preparing the secret key into a modulation coherent state and sending the modulation coherent state to the receiving end; the receiving end receiving the modulation coherent state and obtains a measurement result; the receiving end extracting characteristics of themeasurement result, and using a quantum classifier to predict and obtain category marks; and repeating the above steps until the sending end and the receiving end share the original key, and ending the distribution. The method has the advantages of excellent performance, less occupied resources and better real-time performance, and is also suitable for the existing continuous variable quantum keydistribution system.

Description

technical field [0001] The invention specifically relates to a novel continuous variable quantum key distribution method based on machine learning. Background technique [0002] For more than ten years, continuous variable quantum key distribution has been a research hotspot in quantum cryptography and quantum secure communication. It provides a theoretically perfect way to unconditionally guarantee the communication security between legitimate users in untrusted quantum channels. An absolute advantage of continuous variable quantum key distribution compared to discrete variable quantum key distribution is its compatibility with most modern communication technologies, so continuous variable quantum key distribution can be easily deployed on currently used communication networks . Furthermore, the security of continuously variable quantum key distribution protocols against arbitrary collective attacks has been demonstrated for both asymptotically and finitely long domains, a...

AI Technical Summary

Problems solved by technology

However, the data negotiation, parameter estimation, and error correction processes occupy a large amount of resources of the system, thus seriously affecting the performance of the continuous variable quantum key system, and also seriously affecting the real-time performance of the system

Images