GENERATING AN OUTPUT FOR A RECTIFIED LINEAR UNIT (RELU)-ACTIVATED NEURON OF A NEURAL NETWORK

    公开(公告)号:US20240062053A1

    公开(公告)日:2024-02-22

    申请号:US18260585

    申请日:2021-01-08

    CPC classification number: G06N3/063

    Abstract: In some aspects, a set of input elements is obtained, at a rectified linear unit-activated neuron of a neural network based, on input data at the neuron. A first group and a second group of input elements are generated based on the set of input elements. The first group and the second group of input elements are associated with first weight elements and second weight elements, respectively. A first value is generated based on the first group of input elements and the first weight elements. A second value is generated based on the second group of input elements and the second weight elements. A third value and a fourth value are respectively generated based on a first operation and a second operation on the first value and the second value. An output of the neuron is generated based on the third value and the fourth value.

    DEVICE FOR PROCESSING HOMOMORPHICALLY ENCRYPTED DATA

    公开(公告)号:US20240039694A1

    公开(公告)日:2024-02-01

    申请号:US18254132

    申请日:2021-11-24

    CPC classification number: H04L9/008 G06F9/3875 G06F7/724

    Abstract: There is provided a device for processing homomorphically encrypted data. The device includes: inter-line butterfly array blocks, each inter-line butterfly array block including inter-line modulus butterfly units, each inter-line modulus butterfly unit being configured to perform a modulus butterfly operation based on a computation pair of data points received corresponding to a pair of input data points at a same row of a matrix of input data points; intra-line butterfly array blocks, each intra-line butterfly array block including intra-line modulus butterfly units, each intra-line modulus butterfly unit being configured to perform a modulus butterfly operation based on a computation pair of data points received corresponding to a pair of input data points at a same column of the matrix of input data points; and a clock counter communicatively coupled to each inter-line butterfly array block and each intra-line butterfly array block, and configured to output a counter signal for controlling each inter-line butterfly array block and each intra-line butterfly array block to operate with single cycle initiation interval. The matrix of input data points includes columns of input data points, whereby parallel input data points derived from the homomorphically encrypted data are arranged into the columns of input data points. Furthermore, the inter-line butterfly array blocks and the intra-line butterfly array blocks are arranged in series to form a pipeline for processing the matrix of input data points.

    METHOD AND SYSTEM FOR GENERATING/DECRYPTING CIPHERTEXT, AND METHOD AND SYSTEM FOR SEARCHING CIPHERTEXTS IN A DATABASE
    5.
    发明申请
    METHOD AND SYSTEM FOR GENERATING/DECRYPTING CIPHERTEXT, AND METHOD AND SYSTEM FOR SEARCHING CIPHERTEXTS IN A DATABASE 审中-公开
    用于生成/分解CIPHERTEXT的方法和系统,以及用于在数据库中搜索CIPHERTEXTS的方法和系统

    公开(公告)号:US20170048058A1

    公开(公告)日:2017-02-16

    申请号:US15306072

    申请日:2015-04-23

    Abstract: There is provided a method of generating a ciphertext. The method includes encrypting an input data to produce an encrypted data, and randomizing the encrypted data to produce the ciphertext. In particular, the randomizing process includes performing an exclusive-or (xor) operation on the encrypted data with a cipher pad, whereby the cipher pad is generated based on an xor-homomorphic function of a first key using a second key generated based on the encrypted data. There is also provided a corresponding system for generating a ciphertext, a corresponding method and system for decrypting a ciphertext, and a corresponding method and system for searching ciphertexts in a database, such as at an untrusted server.

    Abstract translation: 提供了生成密文的方法。 该方法包括加密输入数据以产生加密数据,并且随机化加密数据以产生密文。 特别地,随机化处理包括使用密码垫对加密数据执行异或(xor)操作,由此基于第一密钥的XOR同态函数使用基于 加密数据。 还提供了用于生成密文的相应系统,用于解密密文的相应方法和系统,以及用于搜索诸如不受信任的服务器的数据库中的密文的相应方法和系统。

    ENCODING DATA FOR HOMOMORPHIC COMPUTATION AND PERFORMING HOMOMORPHIC COMPUTATION ON ENCODED DATA

    公开(公告)号:US20240171374A1

    公开(公告)日:2024-05-23

    申请号:US18550100

    申请日:2021-03-12

    CPC classification number: H04L9/008 H04L9/06

    Abstract: In some aspects, a method for generating encoded plaintext data in a plaintext vector space includes obtaining a plurality of vectors of plaintext elements, where each plaintext element is an element of a first finite field. The method further includes encoding the plurality of vectors of plaintext elements to a vector of field elements, where each vector of plaintext elements is encoded to a respective field element of the vector of field elements, each of the field elements is an element of a second finite field, and the second finite field is a finite extension field of the first finite field. The method additionally includes encoding the vector of field elements into an element of the plaintext vector space to produce the encoded plaintext data for homomorphic encryption and computation.

    METHOD AND SYSTEM FOR PRIVACY-PRESERVING LOGISTIC REGRESSION TRAINING BASED ON HOMOMORPHICALLY ENCRYPTED CIPHERTEXTS

    公开(公告)号:US20240061955A1

    公开(公告)日:2024-02-22

    申请号:US18260776

    申请日:2021-01-08

    CPC classification number: G06F21/6245 H04L9/008

    Abstract: There is provided a method of privacy-preserving logistic regression training based on homomorphically encrypted ciphertexts. The method includes: obtaining a first packed ciphertext comprising at least a portion of a first training data sample packed into a first vector of slots thereof for training a privacy-preserving logistic regression model; obtaining a second packed ciphertext comprising a plurality of weights of the privacy-preserving logistic regression model packed into a first vector of slots thereof; determining at least a first output probability of the privacy-preserving logistic regression model based on the first packed ciphertext and the second packed ciphertext; and updating the plurality of weights based on the first output probability. There is also provided a corresponding system for privacy-preserving logistic regression training based on homomorphically encrypted data.

Patent Agency Ranking