Liang Ye

Bio: Liang Ye is an academic researcher from Electric Power Research Institute. The author has contributed to research in topics: Risk assessment & Supervised learning. The author has an hindex of 1, co-authored 3 publications receiving 3 citations.

SM9-based attribute encryption method and system

Abstract: The invention discloses the technical field of information security, particularly relates to an SM9-based attribute encryption method and system, and aims to solve the technical problems of high userinformation management overhead, difficulty in maintenance and easiness in leakage of user privacy of an identity label-based encryption algorithm in the prior art. A key generation center generates asystem main private key and a system main public key; the key generation center KGC generates a user private key based on the request of a user B in combination with an attribute set of the user B and the identity identifier of a group where the user B is located; a user A encrypts a message by combining the system main public key and the identity identifier of a group where the user B is located; and the user B decrypts a ciphertext through the user private key to obtain a decryption result. According to the method, the private key and the ciphertext of the user are associated by using a group of attribute sets based on an attribute encryption mechanism, the ciphertext can be decrypted only when the key attribute is matched with the ciphertext attribute, the encryption overhead is not influenced by the number of members in the system, and a more flexible access control structure is provided.

Security Analysis of Power System User Behavior in Big Data Based on Comparative of Neural Network Methods

Abstract: In the context of exponential growth of data information, a large amount of data needs to be effectively processed in the power system intranet to analyze and obtain valuable information. Among them, user behavior is especially important for the security of the entire power system. With the development of large data technology and the wide application of machine learning technology, useful information can be extracted and processed from a large amount of unprocessed data. At the same time, in order to reasonably expand the data set of the relevant samples, traditional mathematical modeling can preprocess the data and integrate the classified output into the sample data set. Finally, this paper selects SSH data as the training set and Local data as the test set, and compares the accuracy of the four machine learning methods in predicting user behavior categories. The ultimate goal is to predict the level of risk of user behavior through the characteristics of user behavior.

Research on Risk Assessment Technology of Power Monitoring System Based on Machine Learning

Abstract: with the complexity of the power system and the increasingly severe network security environment, the industry has urgently needed to improve the risk prediction ability of the power system security and the potential safety hazards brought about by the disposal. According to the experience and the features attributes of historical data, K-means unsupervised learning clustering is carried out. For supervised learning classification, this paper chooses SVM-KNN, and the risk assessment portrait after business disposal is constructed. After establishment and operation of the model, effective and rapid analysis and output of disposal recommendations and corresponding risk levels are carried out, and the original experience is intellectualized and rationalized to the relevant people. In order to make sure the stable, efficient and safe operation of the power monitoring system, model could give prompt safety advice as an expert.

Connection keyword authentication searchable encryption method based on national cryptographic algorithm

Abstract: The invention relates to a connection keyword authentication searchable encryption method based on a national cryptographic algorithm. The method comprises the following steps of: (1) initializing analgorithm; (2) generating a public and private key pair; (3) generating an encryption key through key negotiation; (4) encrypting a document; (5) generating a security index; (6) sending a security list to a cloud server; (7) generating a search token; (8) generating search results; (9) comparing the results; (10) circulating; (11) feeding back the search results; and (12) obtaining a plaintext result. Connection keyword search is supported, it is ensured that a security index can only be generated by a data sender, and keyword guessing attacks of the cloud server are resisted. It is ensured that the token is only matched with the security index sent by the data sender, the ciphertext of the data sender is obtained, the method does not involve bilinear pairing operation with large calculation expenditure when the keyword index is generated, and only one-time bilinear pairing operation is needed when the search token is generated.

Cloud storage data encryption method and system and storage medium

Abstract: The invention discloses a cloud storage data encryption method and system and a storage medium. An encryption user initializes a generated public parameter according to a user access control tree constructed based on a preset user access control strategy and a trusted key generation center, and encrypts the data to be encrypted by using an attribute encryption mode to obtain an encrypted ciphertext, so that a decryption user conforming to the user access control tree decrypts the encrypted ciphertext according to a user private key generated by the trusted key generation center for the decryption user. According to the method, the use of a bilinear pair in an attribute-based encryption system (ABE) is canceled, the efficiency of an attribute-based encryption algorithm can be improved to agreater extent, and the high-efficiency requirement in a cloud storage environment is met.

File processing method, file conversion encryption machine, terminal, server and medium

Abstract: The embodiment of the invention provides a file processing method, a file conversion encryption machine, a terminal, an encryption machine server and a computer readable storage medium. The method canbe applied to a file conversion encryption machine and comprises the steps that an encrypted file, a first secret key ciphertext and first authorization information are obtained, the encrypted file is formed by encrypting an original file through a first secret key, and the first secret key ciphertext is formed by encrypting the first secret key through the first authorization information; the first authorization information is used for representing that the file conversion encryption machine is allowed to use the first key; if the first authorization information passes the verification, thefirst key ciphertext is decrypted by using the first authorization information to obtain a first key; the encrypted file is decrypted based on the decrypted first key to obtain an original file; and the original file is converted into at least one corresponding target format file, wherein the file format of the target format file is different from that of the original file. By adopting the implementation mode, the user operation can be simplified, and the shared file security is improved.