基于深度神经网络和联邦学习的网络入侵检测

在高速网络环境中,对复杂多样的网络入侵进行快速准确的检测成为目前亟待解决的问题。联邦学习作为一种新兴技术,在缩短入侵检测时间与提高数据安全性上取得了很好的效果,同时深度神经网络（DNN）在处理海量数据时具有较好的并行计算能力。结合联邦学习框架并将基于自动编码器优化的DNN作为通用模型,建立一种网络入侵检测模型DFC-NID。对初始数据进行符号数据预处理与归一化处理,使用自动编码器技术对DNN实现特征降维,以得到DNN通用模型模块。利用联邦学习特性使得多个参与方使用通用模型参与训练,训练完成后将参数上传至中心服务器并不断迭代更新通用模型,通过Softmax分类器得到最终的分类预测结果。实验结果表明,DFC-NID模型在NSL-KDD与KDDCup99数据集上的准确率平均达到94.1%,与决策树、随机森林等常用入侵检测模型相比,准确率平均提升3.1%,在攻击类DoS与Probe上,DFC-NID的准确率分别达到99.8%与98.7%。此外,相较不使用联邦学习的NO-FC模型,DFC-NID减少了83.9%的训练时间。     

Feature generation based on relation learning and image partition for occluded person re-identification

In order to solve the challenging tasks of person re-identification(Re-ID) in occluded scenarios, we propose a novel approach which divides local units by forming high-level semantic information of pedestrians and generates features of occluded parts. The approach uses CNN and pose estimation to extract the feature map and key points, and a graph convolutional network to learn the relation of key points. Specifically, we design a Generating Local Part (GLP) module to divide the feature map into different units. Based on different occluded conditions, the partition mode of GLP has high flexibility and variability. The features of the non-occluded parts are clustered into an intermediate node, and then the spatially correlated features of the occluded parts are generated according to the de-clustering operation. We conduct experiments on both the occluded and the holistic datasets to demonstrate its effectiveness.     

Network Intrusion Detection in Internet of Blended Environment Using Ensemble of Heterogeneous Autoencoders (E-HAE)

Contemporary attackers, mainly motivated by financial gain, consistently devise sophisticated penetration techniques to access important information or data. The growing use of Internet of Things (IoT) technology in the contemporary convergence environment to connect to corporate networks and cloud-based applications only worsens this situation, as it facilitates multiple new attack vectors to emerge effortlessly. As such, existing intrusion detection systems suffer from performance degradation mainly because of insufficient considerations and poorly modeled detection systems. To address this problem, we designed a blended threat detection approach, considering the possible impact and dimensionality of new attack surfaces due to the aforementioned convergence. We collectively refer to the convergence of different technology sectors as the internet of blended environment. The proposed approach encompasses an ensemble of heterogeneous probabilistic autoencoders that leverage the corresponding advantages of a convolutional variational autoencoder and long short-term memory variational autoencoder. An extensive experimental analysis conducted on the TON_IoT dataset demonstrated 96.02% detection accuracy. Furthermore, performance of the proposed approach was compared with various single model (autoencoder)-based network intrusion detection approaches: autoencoder, variational autoencoder, convolutional variational autoencoder, and long short-term memory variational autoencoder. The proposed model outperformed all compared models, demonstrating F1-score improvements of 4.99%, 2.25%, 1.92%, and 3.69%, respectively.     

基于One-Shot聚合自编码器的图表示学习

自编码器（AE）是一种高效的图数据表示学习模型,但大多数图自编码器（GAE）为浅层模型,其效率会随着隐藏层的增加而降低。针对上述问题,提出基于One-Shot聚合（OSA）和指数线性（ELU）函数的GAE模型OSA-GAE和图变分自编码器模型OSA-VGAE。首先,利用多层图卷积网络（GCN）构建编码器,并引入OSA和ELU函数;然后,在解码阶段使用内积解码器恢复图的拓扑结构;此外,为了防止模型训练过程中的参数过拟合,在损失函数中引入正则化项。实验结果表明,OSA和ELU函数可以有效提高深层GAE的性能,改善模型的梯度信息传递。在使用6层GCN时,基准引文数据集PubMed的链接预测任务中,深层OSA-VGAE相较于原始的VGAE在ROC曲线下的面积（AUC）和平均精度（AP）上分别提升了8.67和6.85个百分点,深层OSA-GAE相较于原始的GAE在AP和AUC上分别提升了6.82和4.39个百分点。     

基于高分辨率网络和图卷积网络的三维人体重建模型

针对单目图像重建人体时出现的头部姿态翻转和图像特征间隐式空间线索缺失的问题,提出了一种基于高分辨率网络（HRNet）和图卷积网络（GCN）的三维人体重建模型。首先利用HRNet和残差块作为主干网络从原始图像中提取丰富的人体特征信息,然后使用GCN来捕获特征之间隐式的空间线索以获得空间精确的特征表示,最后使用此特征来预测多人线性蒙皮模型（SMPL）的参数以得到更加准确的重建结果;同时为了有效解决人体头部姿态翻转的问题,对SMPL的关节点重新进行了定义,在原有关节的基础上增加对头部关节点的定义。实验结果表明,所提模型能够准确地重建出三维人体,在2D数据集LSP上的重建准确率达到了92.41%,在3D数据集MPI-INF-3DHP上的关节误差和重建误差也大幅降低,平均误差仅分别为97.73 mm和64.63 mm,验证了所提模型在人体重建领域的有效性。     

融合用户需求和边界约束的平面图生成算法

平面图设计是房屋设计的重要过程,而现有的自动化平面图设计方法缺乏考虑用户需求和建筑边界的共同约束,存在生成房间形状缺角、房间之间遮挡严重以及房间超越边界的布局不合理问题。针对上述问题,提出一种融合用户需求和边界约束的房屋平面图生成对抗网络（GBC-GAN）,它由约束布局生成器和房间关系鉴别器构成。首先,将用户指定的房屋布局需求（包括房间数量和类型以及房屋之间的邻接方位关系）转化为约束关系图结构,之后对建筑边界和约束关系图分别编码并进行特征融合;然后,在约束布局生成器中引入边界框预测模块以将平面图生成问题转化为各房间对象边界框生成问题,并利用几何边界优化损失来解决房间之间遮挡严重、房间超越边界的问题;最后,将房间边界框布局和约束关系图输入到房间关系鉴别器训练生成符合房间对象及其关系的平面图布局。在大型真实建筑数据集RPLAN上,该方法的弗雷歇距离（FID）和结构相似性指数（SSIM）比House-GAN方法分别提升了4.39%和2.3%。实验结果表明,在不同用户需求和边界限制条件下,所提方法提高了房屋平面图的合理性和真实性。     

基于贝叶斯优化的无标签网络剪枝算法

针对深度神经网络（DNN）的参数和计算量过大问题,提出一种基于贝叶斯优化的无标签网络剪枝算法。首先,利用全局剪枝策略来有效避免以逐层方式修剪而导致的模型次优压缩率;其次,在网络剪枝过程中不依赖数据样本标签,并通过最小化剪枝网络与基线网络输出特征的距离对网络每层的压缩率进行优化;最后,利用贝叶斯优化算法寻找网络每一层的最优剪枝率,以提高子网搜索的效率和精度。实验结果表明,使用所提算法在CIFAR-10数据集上对VGG-16网络进行压缩,参数压缩率为85.32%,每秒浮点运算次数（FLOPS）压缩率为69.20%,而精度损失仅为0.43%。可见,所提算法可以有效地压缩DNN模型,且压缩后的模型仍能保持良好的精度。     

基于场景先验及注意力引导的跌倒检测算法

已有跌倒检测工作主要关注室内场景,且大多偏重对人员身体姿态特征进行建模,而忽略了场景背景信息以及人员与地面的交互信息。针对这个问题,从实际电梯场景应用入手,提出一种基于场景先验及注意力引导的跌倒检测算法。首先,利用电梯历史数据,以高斯概率分布建模的方式从人员的活动轨迹中自动化地学习场景先验信息;随后,把场景先验信息作为空间注意力掩膜与神经网络的全局特征融合,以此聚焦地面区域的局部信息;然后,将融合后的局部特征与全局特征采用自适应加权的方式进一步聚合,从而形成更具鲁棒性和判别力的特征;最后,将特征送入由全局平均池化层和全连接层构成的分类模块中进行跌倒类别预测。在自构建的电梯场景Elevator Fall Detection和公开的UR Fall Detection数据集上的实验结果表明,所提算法的检测准确率分别达到了95.36%和99.01%,相较于网络结构复杂的ResNet50算法,分别提高了3.52个百分点和0.61个百分点。可见所构建的高斯场景先验引导的注意力机制可使网络关注地面区域的特征,更有利于对跌倒的识别,由此得到的检测模型准确率高且算法满足实时性应用要求。     

CNN parameter design based on fault signal analysis and its application in bearing fault diagnosis

As a representative deep learning network, Convolutional Neural Network (CNN) has been extensively used in bearing fault diagnosis and many good results have been reported. In Prognostics and Health Management (PHM) field, the CNN’s input size is usually designed as a 1D vector or 2D square matrix, and the convolution kernel size is also defined as a square shape like 3 × 3 and 5 × 5, which are directly adopted from the image recognition. Though satisfying results can be obtained, CNN with such parameter specifications is not optimal and efficient. To this end, this paper elaborated the physical characteristics of bearing acceleration signals to guide the CNN design. First, the fault period under different fault types and shaft rotation frequency were used to determine the size of CNN’s input. Next, an exponential function was involved in fitting the envelope of decaying acceleration signal during each fault period, and signal length within different decaying ratios was used to define the CNN’s kernel size. Finally, the designed CNN was validated with the Case Western Reserve University bearing dataset and Paderborn University bearing dataset. Results confirm that the physics-guided CNN (PGCNN) with rectangular input shape and rectangular convolution kernel works better than the baseline CNN with higher accuracy and smaller uncertainty. The feasibility of designing CNN parameters with physics-guided rules derived from bearing fault signal analysis has also been verified.     

Network resource management mechanisms in SDN enabled WSNs: A comprehensive review

Wireless technologies usually have very limited computing, memory, and battery power that require the optimal management of network resources to increase network performance. The optimization of these network resources provides an efficient network topology, traffic control, routing, and data aggregation. This study presents a qualitative and quantitative investigation to evaluate the efficient network resource management mechanisms for software defined wireless sensor networks (SDN-enabled WSNs) from the beginning of network design to reliable data delivery. In this paper, a taxonomy of network resource management research studies is proposed. A detailed analysis of SDN-enabled WSNs architecture, SDN controllers, topology discovery, routing approaches, flow rules installation, and data aggregation is also discussed. Furthermore, the comparative analysis of resource provisioning methods along with various simulation tools is presented. Moreover, this review outlines open research challenges and prospective future directions for network resource management in SDN-enabled WSNs.