| Germplasm resources are strategic resources,and germplasm resources platform can effectively solve the problem of isolated information of germplasm data and realize resource sharing.In the field of germplasm resources,the traditional germplasm resources authentication platform only authenticates through a single server,which is easy to lead to data leakage or loss.In the authentication process,users and platforms are also faced with more potential security problems,such as man-in-the-middle attack,replay attack and denial of service attack.In view of the above security problems faced by traditional germplasm resource platforms,this paper proposes an identity authentication mechanism based on blockchain and face recognition technology.This mechanism integrates the characteristics of blockchain technology,such as decentralization,immutable data and traceable information,as well as the outstanding advantages of face recognition technology in authentication,such as security,fast and hard to counterfeit.Through the consensus mechanism of blockchain and the interaction design of smart contract,it effectively solves the security problems faced by traditional identity authentication.The main research content and summary of this paper are as follows:(1)This paper expounds the security problems existing in the identity authentication mechanism of the traditional germplasm resource platform,analyzes and studies the identity authentication mechanism based on blockchain and face recognition.In the Fabric alliance chain architecture,the improved practical Byzantine fault-tolerant algorithm is adopted to establish a more efficient and secure consensus mechanism,and decentralized identity authentication is realized through the interaction of smart contracts.Due to the functional equivalence of each node of the blockchain,the risk of malicious authentication is effectively reduced and the authentication results are more authentic and credible.(2)FaceNet face recognition model is used to collect and recognize face images.Using CASIA-Web Faces data set as the training set,the accuracy of the model on the LFW data set is about 96%,and the model is not sensitive to face image quality,so it can be well applied to the development of identity authentication system.(3)Collaborative storage of germplasm resource data is conducted through blockchain and IPFS interstellar file system in this paper.User identity information and authentication results are stored on the blockchain,which cannot be easily tampered with and is easy to audit and trace.In addition,due to the large amount of germplasm resources data,the detailed information of germplasm resources data is stored in the interstellar file system and the hash summary of corresponding files is stored on the chain to reduce the storage pressure on the blockchain,which effectively improves the efficiency of data transmission.At last,Hyperledger Caliper architecture is used to test the system performance.The results show that the average latency of the system in read operation reaches 0.58 s,and the TPS of the system reaches a peak value of 26 when the concurrency reaches about 150.When the concurrency is relatively small,the system can basically meet the requirements.Better hardware can also be used to further improve system performance.This paper integrated face recognition and blockchain technology,designed and implemented a secure and reliable identity authentication system for the field of germplasm resources,and better promoted the safe sharing of germplasm resources data and data research.The results show that the system can basically meet the requirements of authentication development in terms of response delay and concurrency performance. |
