Owing to the Network Function Virtualization (NFV) and Software-Defined Networks (SDN), Service Function Chain (SFC) has become a popular service in SDN and NFV-enabled network. However, as the Virtual Network Function (VNF) of each type is generally multi-instance and flows with SFC requests must traverse a series of specified VNFs in predefined orders, it is a challenge for dynamic SFC formation to optimally select VNF instances and construct paths. Moreover, the load balancing and end-to-end delay need to be paid attention to, when routing flows with SFC requests. Additionally, fine-grained scheduling for traffic at flow level needs differentiated routing which should take flow features into consideration. Unfortunately, traditional algorithms cannot fulfill all these requirements. In this paper, we study the Differentiated Routing Problem considering SFC (DRP-SFC) in SDN and NFV-enabled network. We formulate the DRP-SFC as a Binary Integer Programming (BIP) model aiming to minimize the resource consumption costs of flows with SFC requests. Then a novel routing algorithm, Resource Aware Routing Algorithm (RA-RA), is proposed to solve the DRP-SFC. Performance evaluation shows that RA-RA can efficiently solve the DRP-SFC and surpass the performance of other existing algorithms in acceptance rate, throughput, hop count and load balancing.

With the advances of Software-Defined Networks (SDN) and Network Function Virtualization (NFV), Service Function Chain (SFC) has been becoming a popular paradigm to carry and complete network services. Such new computing and networking paradigm enables Virtual Network Functions (VNFs) to be placed in software entities/virtual machines over a network of physical equipments in elastic and flexible way with low capital and operation expenses. VNFs are chained together to steer traffic as needed. However, most of the existing traffic steering and routing path computation algorithms for SFC are complex, unscalable, and low time-efficiency. In this paper, we study the VNF Selection and Chaining Problem (VNF-SCP) in SDN/NFV-enabled networks. We formulate VNF-SCP as a Binary Integer Programming (BIP) model in order to compute routing path for each SFC Request (SFCR) with the minimum end-to-end delay. Then, a novel Deep Learning-based Two-Phase Algorithm (DL-TPA) is introduced, where VNF selection network and VNF chaining network are designed to achieve intelligent and efficient VNF selection and chaining for SFCRs. Performance evaluation shows that DL-TPA can achieve high prediction accuracy and time efficiency of routing path computation, and the overall network performance can be improved significantly.

Distributed Denial of Service (DDoS) attack is threatening network security with increasing number of DDoS attack events. Software Defined Network (SDN), a popular networking paradigm, brings many opportunities to defend against massive network attacks with its centralized control architecture. In this background, this paper proposes a DDoS attack detection and mitigation system, DETPro, which is an efficient and lightweight framework based on decision tree method. In this system, the POX controller and sFlow agents embedded in OpenvSwitch are responsible for network traffic information collection. The DDoS attack detection module implemented with a modified decision tree algorithm is applied to detect DDoS attacks, utilizing Gini impurity and Pessimistic Error Pruning (PEP) strategy. When attacks appear in the network, the DDoS attack mitigation module keeps the major network functionality working with a dynamic white list mechanism, which can timely block attack traffic and assure benign traffic to be served as usual. Experimental results show that DETPro can detect DDoS attack accurately and protect the network from various DDoS attacks effectively.

Benefiting from Network Function Virtualization (NFV), Service Function Chain (SFC) that is composed of a set of ordered Virtual Network Functions (VNFs) has become a popular network service pattern. One of the most important issues for Internet Service Providers (ISPs) is to determine the optimal placement of VNFs and the traffic steering of SFC to optimize the total network cost while guaranteeing resource constraints. In this paper, we study the cost-efficient VNF Placement and Traffic Steering (VNFP-TS) problem. First, we formulate the problem as a Binary Integer Programming (BIP) model aiming to minimize the node running cost, VNF placement cost and communication cost jointly. Then a heuristic Dynamic Programming based Cost Optimization Algorithm (DP-COA) is proposed to divide and conquer the problem. Finally, we evaluate the proposed algorithm by numerical simulations and confirm that DP-COA can achieve high network performance in terms of acceptance rate of SFC Requests (SFCRs) and throughput, and efficiently reduce the total network cost comparing with algorithms in existing literatures.

Energy Harvesting (EH)-based cellular communication has emerged for the merit of simple deployment and continuous energy supply recently. However, the amounts of harvested energy are not always enough to meet the communication requirements of cellular devices. In this paper, we propose an energy cooperation scheme taking advantage of Device-to-Device (D2D) relaying technology, in which those devices with insufficient energy are aided by others to accomplish data transmission. In this scheme, we study the energy efficiency optimization problem, which involves the D2D relay selection, spectrum reusing and power allocation issues. Mathematically, it is formulated as a Mixed-Integer Nonlinear Programming (MINLP) problem, which turns out to be NP-hard. Thus we make a detailed mathematical analysis to the problem and introduce a two-layer optimization algorithm, and based on which, a suboptimal solution with lower computational complexity is then proposed. The simulation results show that the schemes are valid and can achieve significant improvement in system transmission rate and the satisfaction rate of users' communication requirements.

By means of network function virtualization (NFV), dedicated proprietary network devices can be implemented as software and instantiated flexibly on common-off-the-shelf servers, in the form of virtual network functions (VNF). NFV can bring great cost reduction as well as operation flexibility. However, it also brings new problems, one of which is how to meet the availability of network services in the VNF deployment process, because of the error prone nature of software. The availability aware VNF deployment problem has attracted attention by academics, and reserving redundancy has been treated as the de facto technology. Compared with traditional backup schemes for physical machines, resource orchestration in NFV is more flexible and the characteristics of software should be considered to improve resource utilization efficiency. Based on the above considerations, in this paper we further study the availability aware VNF deployment problem in datacenter networks. To improve the resource utilization efficiency, the sharing mechanism of redundancy and multi-tenancy technology are taken into account. Then we formulate the problem mathematically and propose a joint deployment and backup scheme (JDBS). Finally, we conduct a numerical simulation in detail and compare it with four contrasting schemes in the existing literature. The simulation results show that JDBS is obviously superior to the contrasting schemes and can save about 40% resources at most.

Network Function Virtualization (NFV) and Software-Defined Networks (SDN) enable Internet Service Providers (ISPs) to place Virtual Network Functions (VNFs) to achieve the performance and security benefit without incurring high Operating Expenses (OPEX) and Capital Expenses (CAPEX). In NFV environment, Service Function Chains (SFCs) always need to steer the traffic through a series of VNF instances in predefined orders. Moreover, the required number and placement of VNF instances should be optimized to adapt to dynamic network load. Therefore, it is considerable for ISPs to conduct an optimal SFC embedding strategy to improve the network performance and revenue. In the paper, we study the SFC Embedding Problem (SFC-EP) with dynamic VNF placement in geo-distributed cloud system. We formulate this problem as a Binary Integer Programming (BIP) model aiming to embed SFC requests with the minimum embedding cost. Furthermore, the novel SFC eMbedding APproach (SFC-MAP) and VNF Dynamic Release Algorithm (VNF-DRA) have been proposed to efficiently embed SFC requests and optimize the number of placed VNF instances. Performance evaluation results show that the proposed algorithms can provide higher performance in terms of SFC request acceptance rate, network throughput, and mean VNF utilization rate and efficiently reduce the total VNF running time compared with the algorithms in existing literatures.

This work focuses on the problem of editing facial images by manipulating specified attributes of interest. To learn latent representations disentangled with respect to specified face attribute, a novel attribute-disentangled generative model is proposed by combining variational autoencoders (VAEs) and generative adversarial networks (GANs). In the proposed model, only two deep mappings are included: an encoder and a decoder, similarly as the counterparts in the context of VAEs. Latent space mapped by the encoder is split into two parts: style space and attribute space. The former represents attribute-irrelevant factors, such as identity, position, illumination and background, etc. The latter represents the attributes, such as hair color, gender, with or without glasses, etc, of which each dimension represents one single attribute. By regarding constraints on the output of the encoder as discriminative objectives, the encoder can act not only as a discriminator that is expected to discriminate a sample is a real or a generated one, but also as an attribute classifier that can discriminate whether a sample has the specified attributes or not. Combining reconstruction and Kullback-Leibler (KL) divergence regularization losses like in VAEs, the adversarial training loss defined for the style and the attribute in the latent space is introduced, which drives the proposed model to generate images whose distribution are close to the real data distribution in the latent space. Finally, the model was evaluated on the CelebA dataset and experimental results showed its effectiveness in disentangling face attributes and generating high-quality face images.

Network function virtualization (NFV) brings great conveniences and benefits for the enterprises to outsource their network functions to the cloud datacenter. In this paper, we address the virtual network function (VNF) placement problem in cloud datacenter considering users' service function chain requests (SFCRs). To optimize the resource utilization, we take two less-considered factors into consideration, which are the time-varying workloads, and the basic resource consumptions (BRCs) when instantiating VNFs in physical machines (PMs). Then the VNF placement problem is formulated as an integer linear programming (ILP) model with the aim of minimizing the number of used PMs. Afterwards, a Two-StAge heurisTic solution (T-SAT) is designed to solve the ILP. T-SAT consists of a correlation-based greedy algorithm for SFCR mapping (first stage) and a further adjustment algorithm for virtual network function requests (VNFRs) in each SFCR (second stage). Finally, we evaluate T-SAT with the artificial data we compose with Gaussian function and trace data derived from Google's datacenters. The simulation results demonstrate that the number of used PMs derived by T-SAT is near to the optimal results and much smaller than the benchmarks. Besides, it improves the network resource utilization significantly.

Approximate Nearest Neighbor (ANN) search is a challenging problem with the explosive high-dimensional large-scale data in recent years. The promising technique for ANN search include hashing methods which generate compact binary codes by designing effective hash functions. However, lack of an optimal regularization is the key limitation of most of the existing hash functions. To this end, a new method called Adaptive Hashing with Sparse Modification (AHSM) is proposed. In AHSM, codes consist of vertices on the hypercube and the projection matrix is divided into two separate matrices. Data is rotated through a orthogonal matrix first and modified by a sparse matrix. Here the sparse matrix needs to be learned as a regularization item of hash function which is used to avoid overfitting and reduce quantization distortion. Totally, AHSM has two advantages: improvement of the accuracy without any time cost increasement. Furthermore, we extend AHSM to a supervised version, called Supervised Adaptive Hashing with Sparse Modification (SAHSM), by introducing Canonical Correlation Analysis (CCA) to the original data. Experiments show that the AHSM method stably surpasses several state-of-the-art hashing methods on four data sets. And at the same time, we compare three unsupervised hashing methods with their corresponding supervised version (including SAHSM) on three data sets with labels known. Similarly, SAHSM outperforms other methods on most of the hash bits.

By representing data through compact binary encodings, hashing techniques have been widely used for data retrieval because of their large data storage and efficient computational time. Most hashing algorithms typically learn a finite number of data projections, but learning optimal projections remains unaddressed. To deal with this limitation, a novel approach, dubbed Adaptive Hashing with Sparse Modification(AHSM), is proposed that learns binary indices composed of the vertices of hypercube and the projection matrix are comprised of two matrices in this paper. The first matrix is orthogonal for rotating data and the second one is sparse for modifying data. The essence of our scheme is that an optimal transformation of data is learned to minimize quantization distortion and improve model fidelity. AHSM has two contributions: the first one is accuracy improvement, and the second one is no increase on computational complexity. Through experiments, we find that AHSM substantially surpasses several state-of-the-art hashing schemes on three data sets.

Conventional local preserving projection (LPP) is sensitive to outliers because its objective function is based on the L2-norm distance criterion and suffers from the small sample size (SSS) problem. To improve the robustness of LPP against outliers, LPP-L1 uses L1-norm distance metric. However, LPP-L1 does not work ideally when there are larger outliers. We propose a more robust version of LPP, called LPP-MCC, which formulates the objective problem based on maximum correntropy criterion (MCC). The objective problem is efficiently solved via a half-quadratic optimization procedure and the complicated non-linear optimization procedure can thereby be reduced to a simple quadratic optimization at each iteration. Moreover, LPP-MCC avoids the SSS problem because the generalized eigenvalues computation is not involved in the optimization procedure. The experimental results on both synthetic and real-world databases demonstrate that the proposed method can outperform LPP and LPP-L1 when there are large outliers in the training data.

Conventional discriminant locality preserving projection (DLPP) is a dimensionality reduction technique based on manifold learning, which has demonstrated good performance in pattern recognition. However, because its objective function is based on the distance criterion using L2-norm, conventional DLPP is not robust to outliers which are present in many applications. This paper proposes an effective and robust DLPP version based on L1-norm maximization, which learns a set of local optimal projection vectors by maximizing the ratio of the L1-norm-based locality preserving between-class dispersion and the L1-norm-based locality preserving within-class dispersion. The proposed method is proven to be feasible and also robust to outliers while overcoming the small sample size problem. The experimental results on artificial datasets, Binary Alphadigits dataset, FERET face dataset and PolyU palmprint dataset have demonstrated the effectiveness of the proposed method.

Discriminant locality preserving projection (DLPP) is a linear approach that encodes discriminant information into the objective of locality preserving projection and improves its classification ability. To enhance the nonlinear description ability of DLPP, we can optimize the objective function of DLPP in reproducing kernel Hilbert space to form a kernel-based discriminant locality preserving projection (KDLPP). However, KDLPP suffers the following problems: 1) larger computational burden; 2) no explicit mapping functions in KDLPP, which results in more computational burden when projecting a new sample into the low-dimensional subspace; and 3) KDLPP cannot obtain optimal discriminant vectors, which exceedingly optimize the objective of DLPP. To overcome the weaknesses of KDLPP, in this paper, a direct discriminant locality preserving projection with Hammerstein polynomial expansion (HPDDLPP) is proposed. The proposed HPDDLPP directly implements the objective of DLPP in high-dimensional second-order Hammerstein polynomial space without matrix inverse, which extracts the optimal discriminant vectors for DLPP without larger computational burden. Compared with some other related classical methods, experimental results for face and palmprint recognition problems indicate the effectiveness of the proposed HPDDLPP.