面向图神经网络模型提取攻击的图数据生成方法

无数据模型提取攻击是基于攻击者在进行攻击时所需的训练数据信息未知的情况下提出的一类机器学习安全问题。针对无数据模型提取攻击在图神经网络(GNN)领域的研究缺乏,提出分别用GNN可解释性方法GNNExplainer和图数据增强方法GAUG-M优化图节点特征信息和边信息生成所需图数据,最终提取GNN模型的方法。首先,利用GNNExplainer方法对目标模型的响应结果进行可解释性分析得到重要的图节点特征信息;其次,通过对重要的图节点特征加权,对非重要图节点特征降权,实现图节点特征信息的整体优化;然后,使用图形自动编码器作为边信息预测模块,根据优化后的图节点特征得到节点与节点之间的连接概率;最后,根据概率增加或者删减相应边优化边信息。实验采用5个图数据集训练的3种GNN模型架构作为目标模型提取攻击,得到的替代模型达到了73%~87%的节点分类任务准确性和76%~89%的与目标模型性能的一致性,验证了所提方法的有效性。

浅议数据仓库

在分析传统数据库和数据仓库的的区别中介绍了数据仓库的概念,分析数据仓库的体系结构,阐述了数据抽取、转换、清洗、装载的 ETL 过程,介绍企业在定义、建立和使用数据仓库的过程。

Two States CBR Modeling of Data Source in Dynamic Traffic Monitoring Sensor Networks

Real traffic information was analyzed in the statistical characteristics and approximated as a Gaussian time series. A data source model, called two states constant bit rate (TSCBR), was proposed in dynamic traffic monitoring sensor networks. Analysis of autocorrelation of the models shows that the proposed TSCBR model matches with the statistical characteristics of real data source closely. To further verify the validity of the TSCBR data source model, the performance metrics of power consumption and network lifetime was studied in the evaluation of sensor media access control (SMAC) algorithm. The simulation results show that compared with traditional data source models, TSCBR model can significantly improve accuracy of the algorithm evaluation.

Research on stateful public key based secure data aggregation model for wireless sensor networks

Data aggregation technology reduces traffic overhead of wireless sensor network and extends effective working time of the network,yet continued operation of wireless sensor networks increases the probability of aggregation nodes being captured and probability of aggregated data being tampered.Thus it will seriously affect the security performance of the network. For network security issues,a stateful public key based SDAM( secure data aggregation model) is proposed for wireless sensor networks( WSNs),which employs a new stateful public key encryption to provide efficient end-to-end security. Moreover,the security aggregation model will not impose any bound on the aggregation function property,so as to realize the low cost and high security level at the same time.

Model-free conditional independence feature screening for ultrahigh dimensional data

Feature screening plays an important role in ultrahigh dimensional data analysis.This paper is concerned with conditional feature screening when one is interested in detecting the association between the response and ultrahigh dimensional predictors(e.g.,genetic makers)given a low-dimensional exposure variable(such as clinical variables or environmental variables).To this end,we first propose a new index to measure conditional independence,and further develop a conditional screening procedure based on the newly proposed index.We systematically study the theoretical property of the proposed procedure and establish the sure screening and ranking consistency properties under some very mild conditions.The newly proposed screening procedure enjoys some appealing properties.(a)It is model-free in that its implementation does not require a specification on the model structure;(b)it is robust to heavy-tailed distributions or outliers in both directions of response and predictors;and(c)it can deal with both feature screening and the conditional screening in a unified way.We study the finite sample performance of the proposed procedure by Monte Carlo simulations and further illustrate the proposed method through two real data examples.

Research and Realization of Seamless Splicing of Quasi-geoid

Considering the differences in area, precision, datum and resolution existing among the national, provincial and urban quasi-geoids, some methods such as datum transformation and weighting according to precision are presented in this paper to normalize the quasi-geoid models with different areas, precisions, datums and resolutions. In this way, the seamless splicing of quasi-geoid is realized.