基于不平衡数据深度信念网络的并行入侵检测方法和系统

    公开(公告)号:WO2022012144A1

    公开(公告)日:2022-01-20

    申请号:PCT/CN2021/094023

    申请日:2021-05-17

    Applicant: 湖南大学

    Abstract: 本发明公开了一种基于不平衡数据深度信念网络的并行入侵检测方法,其读取不平衡数据集数据,对不平衡数据采用改进的NCL算法进行欠采样处理,降低多数类样本的比重,使数据集数据分布均衡;在分布式内存计算平台Spark平台上采用改进的差分进化算法对深度信念网络模型的参数进行优化,得到最优的模型参数;对数据集数据进行特征提取,然后采用加权后的核极限学习机进行入侵检测分类,最后通过多线程并行的训练多个不同结构的加权后的核极限学习机作为基分类器,建立基于自适应加权投票的多分类器入侵检测模型进行并行入侵检测。本发明能解决现有入侵检测方法对不平衡数据集缺乏针对性、训练时间过长的技术问题,并提高优化深度信念网络模型参数的速度。

    WATERMARK AS HONEYPOT FOR ADVERSARIAL DEFENSE

    公开(公告)号:WO2021242584A1

    公开(公告)日:2021-12-02

    申请号:PCT/US2021/033106

    申请日:2021-05-19

    Applicant: PAYPAL, INC.

    Inventor: ZHANG, Jiyi

    Abstract: Systems, methods, and computer program products for determining an attack on a neural network. A data sample is received at a first classifier neural network and at a watermark classifier neural network, wherein the first classifier neural network is trained using a first dataset and a watermark dataset. The first classifier neural network determines a classification label for the data sample. A watermark classifier neural network determines a watermark classification label for the data sample. A data sample is determined as an adversarial data sample based on the classification label for the data sample and the watermark classification label for the data sample.

    SYSTEM AND METHODS TO OPTIMIZE NEURAL NETWORKS USING SENSOR FUSION

    公开(公告)号:WO2021259806A1

    公开(公告)日:2021-12-30

    申请号:PCT/EP2021/066675

    申请日:2021-06-18

    Abstract: A method for optimizing a neural network is provided, including: (1) capturing, via a first sensor group having a first field of view, a first sample set having a first sensor domain corresponding to the first field of view; (2) capturing, via a second sensor group having a second field of view, a second sample set having a second sensor domain corresponding to the second field of view; (3) generating regions of interest of the second sample set; (4) translating the regions of interest to the first sensor domain; (5) identifying nodes of the neural network which correspond to the translated regions; and (6) optimizing the neural network by at least one of (a) increasing the weight value of the nodes corresponding to the one or more translated regions and (b) decreasing the weight value of the nodes not corresponding to the one or more translated regions.

    数据异常检测方法、装置、设备及存储介质

    公开(公告)号:WO2021139249A1

    公开(公告)日:2021-07-15

    申请号:PCT/CN2020/118524

    申请日:2020-09-28

    Inventor: 邓悦 郑立颖 徐亮

    Abstract: 一种数据异常检测方法、装置、设备及存储介质,涉及大数据领域,该方法包括:获取未标记数据(S1);根据预设的查询策略从所述未标记数据中提取出初级异常数据(S2);将所述初级异常数据进行识别标记后存入已标记的第一数据集合中组成第二数据集合,并通过所述第二数据集合对预先训练的超球体分类模型进行训练(S3);识别所述超球体分类模型是否达到训练终止条件(S4);当达到所述训练终止条件,将所述未标记数据输入训练终止条件下的所述超球体分类模型中进行分类筛选,以得到目标异常数据(S5)。该方法利用少量已标记数据训练分类模型,达到训练终止条件后利用该分类模型对未标记数据进行分类,对数据的原始分布没有限制,减少了运营人员需要标记的数据量,分类结果准确度高。

Patent Agency Ranking