Search

Single sample per person face recognition (SSPP FR) is one of the most challenging problems in FR due to the extreme lack of enrolment data. State-of-the-art SSPP FR methods are based on the prototype plus variation (i.e., P+V) model. However, the classic P+V model has two major limitations: 1) It is a linear model and cannot generalize many non-linear variations; 2) It can be severely impaired once the enrolment face images are contaminated with variations. To this end, we propose a novel disentangled prototype plus variation model, dubbed DisP+V, to tackle such limitations. DisP+V consists of an encoder-decoder structural generator and two discriminators. The generator and discriminators play two adversarial games such that the generator nonlinearly encodes the images into a latent semantic space, where the more discriminative prototype feature and the less discriminative variation feature are disentangled. Meanwhile, the prototype and variation features in the latent space can guide the generator to generate an identity-preserved prototype and the corresponding variation, respectively. Experiments on various real-world face datasets demonstrate the superiority of our DisP+V model over the classic P+V model for SSPP FR. Furthermore, DisP+V demonstrates its unique characteristics in the challenging prototype recovery task.

Federated learning (FL) is a popular distributed learning framework that can reduce privacy risks by not explicitly sharing private data. However, recent works have demonstrated that sharing model updates makes FL vulnerable to inference attack. In this work, we show our key observation that the data representation leakage from gradients is the essential cause of privacy leakage in FL. We also provide an analysis of this observation to explain how the data presentation is leaked. Based on this observation, we propose a defense called Soteria against model inversion attack in FL. The key idea of our defense is learning to perturb data representation such that the quality of the reconstructed data is severely degraded, while FL performance is maintained. In addition, we derive a certified robustness guarantee to FL and a convergence guarantee to FedAvg, after applying our defense. To evaluate our defense, we conduct experiments on MNIST and CIFAR10 for defending against the DLG attack and GS attack. Without sacrificing accuracy, the results demonstrate that our proposed defense can increase the mean squared error between the reconstructed data and the raw data by as much as 160× for both DLG attack and GS attack, compared with baseline defense methods. Therefore, the privacy of the FL system is significantly improved. Our code can be found at https://github.com/jeremy313/Soteria.

This paper presents a design approach for fast- locking and low jitter self-biased phase-locked loop (PLL). The charge-pump current injection technology with minimum area overhead is adopted to accelerate the loop equilibrium capture process without sacrificing the jitter performance. A start-up circuit is proposed in order to shorten the initial ramping up interval of the voltage-controlled oscillator (VCO), which will also help in reducing the lock-in time. A proportional coefficient is introduced in designing self-biased PLLs, which provides more flexibility regarding practical circuits design. The proposed fast- locking self-biased PLL is designed in a TSMC 28nm CMOS process with a supply voltage of 0.9 V. The simulation results show that the locking time is reduced by up to 85% for large division ratios and should not deteriorate the capture performance in small division ratios. Meanwhile, the system almost has no increase in area and the locking time is reduced from 24us to about 3us when operating at 6GHz.

This paper analyzes a bridge arm overcurrent accident in a flexible DC converter station. First, the principle of protection division and configuration of converter station is introduced and the principle of overcurrent protection of bridge arm is clarified. Then, the background of the accident is introduced in detail, the fault characteristics of the no-load charging current of the AC energy dissipation device transformer is identified based on the time scale. And the positive and negative low-frequency oscillating currents are superimposed, compared and analyzed. It is concluded that the resonance caused by the impedance matching between the positive and negative converters causes the action of overcurrent protection of the bridge arm, which has certain reference value for analyzing the converter oscillation risk in actual flexible DC projects.

Modular multilevel converter (MMC) can provide dynamic reactive power and voltage support for the grid during a quick AC voltage drop. However, restrains due to current capability of MMC should not be ignored. A constant reactive power and voltage control mode of MMC is of slow dynamic response and may produce transient impact. This paper focuses on reactive power control strategy of MMC, and a novel control mode combined modified constant AC voltage control and reactive power control is designed. An auxiliary control loop is added with current limitation, and a post-fault integral instantaneous reset control is introduced to suppress the transient impact after voltage recovery. The control strategy is used in Zhangbei $\pm 500\mathrm{k}\mathrm{V}$ four-terminal MMC HVDC power grid simulation model. Results show that the novel control strategy can provide converter station with much stronger reactive power support capability in contrast to the constant reactive control. It empowers converter station to regulate its reactive power quickly and smoothly. The strategy is effective at limiting MMC over-current and can relieve AC over-voltage transient impact after voltage recovery.

A parameter optimization method of MMC(Modular Multilevel Converter) controls based on firefly algorithm is proposed in this paper. First, a simplified small signal mathematical model which contains primary structure of MMC HVDC system, control loops and measurements is built. Then an objective function is set to optimize active and reactive power response of converters while considering DC voltage at the same time. An optimization method based on firefly algorithm is designed for the model. Finally a case study of MMC HVDC shows, active and reactive power response of converters at both ends are improved by control parameters optimization.

Hyperparameters are critical in machine learning, as different hyperparameters often result in models with significantly different performance. Hyperparameters may be deemed confidential because of their commercial value and the confidentiality of the proprietary algorithms that the learner uses to learn them. In this work, we propose attacks on stealing the hyperparameters that are learned by a learner. We call our attacks hyperparameter stealing attacks. Our attacks are applicable to a variety of popular machine learning algorithms such as ridge regression, logistic regression, support vector machine, and neural network. We evaluate the effectiveness of our attacks both theoretically and empirically. For instance, we evaluate our attacks on Amazon Machine Learning. Our results demonstrate that our attacks can accurately steal hyperparameters. We also study countermeasures. Our results highlight the need for new defenses against our hyperparameter stealing attacks for certain machine learning algorithms., In the 39th IEEE Symposium on Security and Privacy (IEEE S & P), May 2018

Detecting fraudulent users in online social networks is a fundamental and urgent research problem as adversaries can use them to perform various malicious activities. Global social structure based methods, which are known as guilt-by-association, have been shown to be promising at detecting fraudulent users. However, existing guilt-by-association methods either assume symmetric (i.e., undirected) social links, which oversimplifies the asymmetric (i.e., directed) social structure of real-world online social networks, or only leverage labeled fraudulent users or labeled normal users (but not both) in the training dataset, which limits detection accuracies. In this work, we propose GANG, a guilt-by-association method on directed graphs, to detect fraudulent users in OSNs. GANG is based on a novel pairwise Markov Random Field that we design to capture the unique characteristics of the fraudulent-user-detection problem in directed OSNs. In the basic version of GANG, given a training dataset, we leverage Loopy Belief Propagation (LBP) to estimate the posterior probability distribution for each user and uses it to predict a user's label. However, the basic version is not scalable enough and not guaranteed to converge because it relies on LBP. Therefore, we further optimize GANG and our optimized version can be represented as a concise matrix form, with which we are able to derive conditions for convergence. We compare GANG with various existing guilt-by-association methods on a large-scale Twitter dataset and a large-scale Sina Weibo dataset with labeled fraudulent and normal users. Our results demonstrate that GANG substantially outperforms existing methods, and that the optimized version of GANG is significantly more efficient than the basic version.

In order to study the application of VSC-MTDC in hydropower transmission, make full use of the advantages of VSC-HVDC, established VSC-MTDC hydropower in transportion system model, the analysis of the mathematical model and control strategy. Finally, the three terminal system is simulated by PSCAD, verified the conservation of power system, and analyzes the influence of system of three-phase short circuit. After the flexible DC transmission system is adopted, the power generation can be optimized by interconnecting with the power grid, and the power generation efficiency of the hydropower station can be effectively improved.

Online social networks are known to be vulnerable to the so-called Sybil attack, in which an attacker maintains massive fake accounts (also called Sybils) and uses them to perform various malicious activities. Therefore, Sybil detection is a fundamental security research problem in online social networks. Random walk based methods, which leverage the structure of an online social network to distribute reputation scores for users, have been demonstrated to be promising in certain real-world online social networks. In particular, random walk based methods have three desired features: they can have theoretically guaranteed performance for online social networks that have the fast-mixing property, they are accurate when the social network has strong homophily property, and they can be scalable to large-scale online social networks. However, existing random walk based methods suffer from several key limitations: 1) they can only leverage either labeled benign users or labeled Sybils, but not both, 2) they have limited detection accuracy for weak-homophily social networks, and 3) they are not robust to label noise in the training dataset. In this work, we propose a new random walk based Sybil detection method called SybilWalk. SybilWalk addresses the limitations of existing random walk based methods while maintaining their desired features. We perform both theoretical and empirical evaluations to compare SybilWalk with previous random walk based methods. Theoretically, for online social networks with the fast-mixing property, SybilWalk has a tighter asymptotical bound on the number of Sybils that are falsely accepted into the social network than all existing random walk based methods. Empirically, we compare SybilWalk with previous random walk based methods using both social networks with synthesized Sybils and a large-scale Twitter dataset with real Sybils. Our empirical results demonstrate that 1) SybilWalk is substantially more accurate than existing random walk based methods for weakhomophily social networks, 2) SybilWalk is substantially more robust to label noise than existing random walk based methods, and 3) SybilWalk is as scalable as the most efficient existing random walk based methods. In particular, on the Twitter dataset, SybilWalk achieves a false positive rate of 1.3% and a false negative rate of 17.3%.

Detecting Sybils in online social networks (OSNs) is a fundamental security research problem as adversaries can leverage Sybils to perform various malicious activities. Structure-based methods have been shown to be promising at detecting Sybils. Existing structure-based methods can be classified into two categories: Random Walk (RW)-based methods and Loop Belief Propagation (LBP)-based methods. RW-based methods cannot leverage labeled Sybils and labeled benign users simultaneously, which limits their detection accuracy, and they are not robust to noisy labels. LBP-based methods are not scalable, and they cannot guarantee convergence. In this work, we propose SybilSCAR, a new structure-based method to perform Sybil detection in OSNs. SybilSCAR maintains the advantages of existing methods while overcoming their limitations. Specifically, SybilSCAR is Scalable, Convergent, Accurate, and Robust to label noises. We first propose a framework to unify RW-based and LBP-based methods. Under our framework, these methods can be viewed as iteratively applying a (different) local rule to every user, which propagates label information among a social graph. Second, we design a new local rule, which SybilSCAR iteratively applies to every user to detect Sybils. We compare SybilSCAR with a state-of-the-art RW-based method and a state-of-the-art LBP-based method, using both synthetic Sybils and large-scale social network datasets with real Sybils. Our results demonstrate that SybilSCAR is more accurate and more robust to label noise than the compared state-of-the-art RW-based method, and that SybilSCAR is orders of magnitude more scalable than the state-of-the-art LBP-based method and is guaranteed to converge. To facilitate research on Sybil detection, we have made our implementation of SybilSCAR publicly available on our webpages.

We aim to study the subspace structure of dataapproximately generated from multiple categories and removeerrors (e.g., noise, corruptions, and outliers) in the data aswell. Most previous methods for subspace analysis learn onlyone subspace, failing to discover the intrinsic complex structure, while state-of-the-art methods use data itself as the basis (self-expressiveness property), showing degraded performance whendata contain errors. To tackle the problem, we propose anovel method, called Matrix Factorization with Column L0-normconstraint (MFC0), from the matrix factorization perspective. MFC0 simultaneously discovers the multi-subspace structure ofeither clean or contaminated data, and learns the basis for eachsubspace. Speciflcally, the learnt basis with the orthonormal constraint shows high robustness to errors by adding a regularizationterm. Owing to the column l0-norm constraint, the generatedrepresentation matrix can be (approximate) block-diagonal afterreordering its columns, with each block characterizing onesubspace. We develop an efflcient flrst-order optimization schemeto stably solve the nonconvex and nonsmooth objective function ofMFC0. Experimental results on synthetic data and real-world facedatasets demonstrate the superiority over traditional and state-of-the-art methods on both representation learning, subspacerecovery and clustering.

Matrix factorization techniques have been frequently utilized in pattern recognition and machine learning. Among them, Non-negative Matrix Factorization (NMF) has received considerable attention because it represents the naturally occurring data by parts of it. On the other hand, from the geometric perspective, the data is usually sampled from a low dimensional manifold embedded in a high dimensional ambient space. One hopes then to find a compact representation which uncovers the intrinsic geometric structure. In this paper, we propose a novel method, called Graph Regularized Non-negative Matrix Factorization with Sparse Coding (GRNMF_SC), the new model can learn much sparser representation and more discriminating power via imposing sparse constraint and Laplacian regularization explicitly. Experimental results on the ORL and Yale databases demonstrate encouraging performance of the proposed algorithm when compared with the state-of-the-art algorithms.

Internet of Things (IoT) aims to connect everything at anywhere and anytime, in which objects need to be mapped from the physical world to the cyber world for further processing. Time and space characteristics are the basic features of objects in the physical world, and are significant for objects' physical-cyber world mapping. However, space-time data is usually formatted in different ways, and may not be precise enough in some cases due to the variety of technologies and systems. In this paper, we study the space-time registration for a single IoT application (i.e., Unit IoT) and multiple IoT applications (i.e., Ubiquitous IoT). Meanwhile, space-time consistency is discussed in U2IoT (i.e., Unit IoT, and Ubiquitous IoT). Moreover, a case study is discussed to present trajectory estimation in the airport scenario, and indicate the importance of space-time data when objects are mapped from the physical world to the cyber world by different methods for IoT ubiquitous connection.

Aim at the small-sample events of the torsional fault in marine, a method of shaft torsional vibration fault diagnosis in marine is proposed based on the theories of Shannon entropy of WT (Wavelet Packet) and DAGSVM (Directed Acyclic Graph Support Vector Machine). Firstly, the signals of four torsional vibration fault patterns are extracted relying on experimental platform of shaft torsional vibration in marine; then, extract the Shannon entropy of WPT for the input eigenvectors of SVM; Finally, identify the faults by using the SVM which advanced by the K-CV (K-fold Cross Validation) . The result shows that the method has higher recognition rate, providing a valuable on-line diagnostic method for the shaft torsional vibration fault diagnosis in marine.