arXiv subjects

Zixuan Wang

Publications and source records attributed to Zixuan Wang.

At least 163 records · Page 9Linked to original sources

arXiv2023

Optimal Repair Strategy Against Advanced Persistent Threats Under Time-Varying Networks

Advanced persistent threat (APT) is a kind of stealthy, sophisticated, and long-term cyberattack that has brought severe financial losses and critical infrastructure damages. Existing works mainly focus on APT defense under stable network topologies, while the problem under time-varying dynamic networks (e.g., vehicular networks) remains unexplored, which motivates our work. Besides, the spatiotemporal dynamics in defense resources, complex attackers' lateral movement behaviors, and lack of timely defense make APT defense a challenging issue under time-varying networks. In this paper, we propose a novel game-theoretical APT defense approach to promote real-time and optimal defense strategy-making under both periodic time-varying and general time-varying environments. Specifically, we first model the interactions between attackers and defenders in an APT process as a dynamic APT repair game, and then formulate the APT damage minimization problem as the precise prevention and control (PPAC) problem. To derive the optimal defense strategy under both latency and defense resource constraints, we further devise an online optimal control-based mechanism integrated with two backtracking-forward algorithms to fastly derive the near-optimal solution of the PPAC problem in real time. Extensive experiments are carried out, and the results demonstrate that our proposed scheme can efficiently obtain optimal defense strategy in 54481 ms under seven attack-defense interactions with 9.64$\%$ resource occupancy in stimulated periodic time-varying and general time-varying networks. Besides, even under static networks, our proposed scheme still outperforms existing representative APT defense approaches in terms of service stability and defense resource utilization.

cs.GT↗

arXiv2023

FedEdge AI-TC: A Semi-supervised Traffic Classification Method based on Trusted Federated Deep Learning for Mobile Edge Computing

As a typical entity of MEC (Mobile Edge Computing), 5G CPE (Customer Premise Equipment)/HGU (Home Gateway Unit) has proven to be a promising alternative to traditional Smart Home Gateway. Network TC (Traffic Classification) is a vital service quality assurance and security management method for communication networks, which has become a crucial functional entity in 5G CPE/HGU. In recent years, many researchers have applied Machine Learning or Deep Learning (DL) to TC, namely AI-TC, to improve its performance. However, AI-TC faces challenges, including data dependency, resource-intensive traffic labeling, and user privacy concerns. The limited computing resources of 5G CPE further complicate efficient classification. Moreover, the "black box" nature of AI-TC models raises transparency and credibility issues. The paper proposes the FedEdge AI-TC framework, leveraging Federated Learning (FL) for reliable Network TC in 5G CPE. FL ensures privacy by employing local training, model parameter iteration, and centralized training. A semi-supervised TC algorithm based on Variational Auto-Encoder (VAE) and convolutional neural network (CNN) reduces data dependency while maintaining accuracy. To optimize model light-weight deployment, the paper introduces XAI-Pruning, an AI model compression method combined with DL model interpretability. Experimental evaluation demonstrates FedEdge AI-TC's superiority over benchmarks in terms of accuracy and efficient TC performance. The framework enhances user privacy and model credibility, offering a comprehensive solution for dependable and transparent Network TC in 5G CPE, thus enhancing service quality and security.

cs.CR↗

arXiv2023

Hard Sample Mining Enabled Supervised Contrastive Feature Learning for Wind Turbine Pitch System Fault Diagnosis

The efficient utilization of wind power by wind turbines relies on the ability of their pitch systems to adjust blade pitch angles in response to varying wind speeds. However, the presence of multiple health conditions in the pitch system due to the long-term wear and tear poses challenges in accurately classifying them, thus increasing the maintenance cost of wind turbines or even damaging them. This paper proposes a novel method based on hard sample mining-enabled supervised contrastive learning (HSMSCL) to address this problem. The proposed method employs cosine similarity to identify hard samples and subsequently, leverages supervised contrastive learning to learn more discriminative representations by constructing hard sample pairs. Furthermore, the hard sample mining framework in the proposed method also constructs hard samples with learned representations to make the training process of the multilayer perceptron (MLP) more challenging and make it a more effective classifier. The proposed approach progressively improves the fault diagnosis model by introducing hard samples in the SCL and MLP phases, thus enhancing its performance in complex multi-class fault diagnosis tasks. To evaluate the effectiveness of the proposed method, two real datasets comprising wind turbine pitch system cog belt fracture data are utilized. The fault diagnosis performance of the proposed method is compared against existing methods, and the results demonstrate its superior performance. The proposed approach exhibits significant improvements in fault diagnosis performance, providing promising prospects for enhancing the reliability and efficiency of wind turbine pitch system fault diagnosis.

cs.LG↗

arXiv2023

IWEK: An Interpretable What-If Estimator for Database Knobs

The knobs of modern database management systems have significant impact on the performance of the systems. With the development of cloud databases, an estimation service for knobs is urgently needed to improve the performance of database. Unfortunately, few attentions have been paid to estimate the performance of certain knob configurations. To fill this gap, we propose IWEK, an interpretable & transferable what-if estimator for database knobs. To achieve interpretable estimation, we propose linear estimator based on the random forest for database knobs for the explicit and trustable evaluation results. Due to its interpretability, our estimator capture the direct relationships between knob configuration and its performance, to guarantee the high availability of database. We design a two-stage transfer algorithm to leverage historical experiences to efficiently build the knob estimator for new scenarios. Due to its lightweight design, our method can largely reduce the overhead of collecting training data and could achieve cold start knob estimation for new scenarios. Extensive experiments on YCSB and TPCC show that our method performs well in interpretable and transferable knob estimation with limited training data. Further, our method could achieve efficient estimator transfer with only 10 samples in TPCC and YSCB.

cs.DB↗

arXiv2023

COLA: Characterizing and Optimizing the Tail Latency for Safe Level-4 Autonomous Vehicle Systems

Autonomous vehicles (AVs) are envisioned to revolutionize our life by providing safe, relaxing, and convenient ground transportation. The computing systems in such vehicles are required to interpret various sensor data and generate responses to the environment in a timely manner to ensure driving safety. However, such timing-related safety requirements are largely unexplored in prior works. In this paper, we conduct a systematic study to understand the timing requirements of AV systems. We focus on investigating and mitigating the sources of tail latency in Level-4 AV computing systems. We observe that the performance of AV algorithms is not uniformly distributed -- instead, the latency is susceptible to vehicle environment fluctuations, such as traffic density. This contributes to burst computation and memory access in response to the traffic, and further leads to tail latency in the system. Furthermore, we observe that tail latency also comes from a mismatch between the pre-configured AV computation pipeline and the dynamic latency requirements in real-world driving scenarios. Based on these observations, we propose a set of system designs to mitigate AV tail latency. We demonstrate our design on widely-used industrial Level-4 AV systems, Baidu Apollo and Autoware. The evaluation shows that our design achieves 1.65 X improvement over the worst-case latency and 1.3 X over the average latency, and avoids 93% of accidents on Apollo.

cs.RO↗

arXiv2023

LA3: Efficient Label-Aware AutoAugment

Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing work focuses on constructing a unified policy applicable to all data samples in a given dataset, without considering sample or class variations. In this paper, we propose a novel two-stage data augmentation algorithm, named Label-Aware AutoAugment (LA3), which takes advantage of the label information, and learns augmentation policies separately for samples of different labels. LA3 consists of two learning stages, where in the first stage, individual augmentation methods are evaluated and ranked for each label via Bayesian Optimization aided by a neural predictor, which allows us to identify effective augmentation techniques for each label under a low search cost. And in the second stage, a composite augmentation policy is constructed out of a selection of effective as well as complementary augmentations, which produces significant performance boost and can be easily deployed in typical model training. Extensive experiments demonstrate that LA3 achieves excellent performance matching or surpassing existing methods on CIFAR-10 and CIFAR-100, and achieves a new state-of-the-art ImageNet accuracy of 79.97% on ResNet-50 among auto-augmentation methods, while maintaining a low computational cost.

cs.CV↗

arXiv2023

Gamify Stencil Dwarf on Cloud for Democratizing Scientific Computing

Stencil computation is one of the most important kernels in various scientific computing. Nowadays, most Stencil-driven scientific computing still relies heavily on supercomputers, suffering from expensive access, poor scalability, and duplicated optimizations. This paper proposes Tetris, the first system for high-performance Stencil on heterogeneous CPU+GPU, towards democratizing Stencil-driven scientific computing on Cloud. In Tetris, polymorphic tiling tetrominoes are first proposed to bridge different hardware architectures and various application contexts with a perfect spatial and temporal tessellation automatically. Tetris is contributed by three main components: (1) Underlying hardware characteristics are first captured to achieve a sophisticated Pattern Mapping by register-level tetrominoes; (2) An efficient Locality Enhancer is first presented for data reuse on spatial and temporal dimensions simultaneously by cache/SMEM-level tetrominoes; (3) A novel Concurrent Scheduler is first designed to exploit the full potential of on-cloud memory and computing power by memory-level tetrominoes. Tetris is orthogonal to (and complements) the optimizations or deployments for a wide variety of emerging and legacy scientific computing applications. Results of thermal diffusion simulation demonstrate that the performance is improved by 29.6x, reducing time cost from day to hour, while preserving the original accuracy.

cs.DC↗

arXiv2023

Understanding Edge-of-Stability Training Dynamics with a Minimalist Example

Recently, researchers observed that gradient descent for deep neural networks operates in an ``edge-of-stability'' (EoS) regime: the sharpness (maximum eigenvalue of the Hessian) is often larger than stability threshold $2/η$ (where $η$ is the step size). Despite this, the loss oscillates and converges in the long run, and the sharpness at the end is just slightly below $2/η$. While many other well-understood nonconvex objectives such as matrix factorization or two-layer networks can also converge despite large sharpness, there is often a larger gap between sharpness of the endpoint and $2/η$. In this paper, we study EoS phenomenon by constructing a simple function that has the same behavior. We give rigorous analysis for its training dynamics in a large local region and explain why the final converging point has sharpness close to $2/η$. Globally we observe that the training dynamics for our example has an interesting bifurcating behavior, which was also observed in the training of neural nets.

cs.LG↗

arXiv2022

Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability

Recent findings (e.g., arXiv:2103.00065) demonstrate that modern neural networks trained by full-batch gradient descent typically enter a regime called Edge of Stability (EOS). In this regime, the sharpness, i.e., the maximum Hessian eigenvalue, first increases to the value 2/(step size) (the progressive sharpening phase) and then oscillates around this value (the EOS phase). This paper aims to analyze the GD dynamics and the sharpness along the optimization trajectory. Our analysis naturally divides the GD trajectory into four phases depending on the change of the sharpness. We empirically identify the norm of output layer weight as an interesting indicator of sharpness dynamics. Based on this empirical observation, we attempt to theoretically and empirically explain the dynamics of various key quantities that lead to the change of sharpness in each phase of EOS. Moreover, based on certain assumptions, we provide a theoretical proof of the sharpness behavior in EOS regime in two-layer fully-connected linear neural networks. We also discuss some other empirical findings and the limitation of our theoretical results.

cs.LG↗

arXiv2022

Large Single-Phonon Optomechanical Coupling between Quantum Dots and Tightly Confined Surface Acoustic Waves in the Quantum Regime

Surface acoustic waves (SAWs) coupled to quantum dots (QDs), trapped atoms and ions, and point defects have been proposed as quantum transduction platforms, yet the requisite coupling rates and cavity lifetimes have not been experimentally established. Although the interaction mechanism varies, small acoustic cavities with large zero-point motion are required for high efficiencies. We experimentally establish the feasibility of this platform through electro- and opto-mechanical characterization of tightly focusing, single-mode Gaussian SAW cavities at $\sim$3.6 GHz on GaAs. We explore the performance limits of the platform by fabricating SAW cavities with mode volumes approaching 6$λ^3$ and linewidths $\leq$1 MHz. Employing strain-coupled single InAs QDs as optomechanical intermediaries, we measure single-phonon optomechanical coupling rates $g_0 \approx 2π\times 1.2$ MHz. Sideband scattering rates thus exceed intrinsic phonon loss, indicating the potential for quantum optical readout and transduction of cavity phonon states. To demonstrate the feasibility of this platform for low-noise ground-state quantum transduction, we develop a fiber-based confocal microscope in a dilution refrigerator and perform single-QD resonance fluorescence sideband spectroscopy at mK temperatures. These measurements show conversion between microwave phonons and optical photons with sub-natural linewidths.

physics.app-ph↗

arXiv2022

Explicit and implicit models in infrared and visible image fusion

Infrared and visible images, as multi-modal image pairs, show significant differences in the expression of the same scene. The image fusion task is faced with two problems: one is to maintain the unique features between different modalities, and the other is to maintain features at various levels like local and global features. This paper discusses the limitations of deep learning models in image fusion and the corresponding optimization strategies. Based on artificially designed structures and constraints, we divide models into explicit models, and implicit models that adaptively learn high-level features or can establish global pixel associations. Ten models for comparison experiments on 21 test sets were screened. The qualitative and quantitative results show that the implicit models have more comprehensive ability to learn image features. At the same time, the stability of them needs to be improved. Aiming at the advantages and limitations to be solved by existing algorithms, we discuss the main problems of multi-modal image fusion and future research directions.

cs.CV↗

arXiv2022

Residual-guided Personalized Speech Synthesis based on Face Image

Previous works derive personalized speech features by training the model on a large dataset composed of his/her audio sounds. It was reported that face information has a strong link with the speech sound. Thus in this work, we innovatively extract personalized speech features from human faces to synthesize personalized speech using neural vocoder. A Face-based Residual Personalized Speech Synthesis Model (FR-PSS) containing a speech encoder, a speech synthesizer and a face encoder is designed for PSS. In this model, by designing two speech priors, a residual-guided strategy is introduced to guide the face feature to approach the true speech feature in the training. Moreover, considering the error of feature's absolute values and their directional bias, we formulate a novel tri-item loss function for face encoder. Experimental results show that the speech synthesized by our model is comparable to the personalized speech synthesized by training a large amount of audio data in previous works.

cs.SD↗

arXiv2022

A simple criterion and experiments for onset of flocculation in kaolin clay suspensions

Cohesive effects between fine-grained sediment particles greatly influence their effective settling rate and erodibility. Many studies have observed a qualitative difference in settling dynamics between clays in freshwater, where particles remain dispersed, and in saltwater, where aggregates form and settle rapidly. The critical coagulation concentration (CCC) of salt that separates the two regimes however remains under-investigated, even though knowledge of the CCC is crucial to understanding aggregation in settings such as estuaries, where large salt concentration gradients occur. Furthermore, no simple criterion exists to predict the CCC for clay suspensions. In this study, systematic experiments are performed to determine the CCC, by measuring transmitted light intensity through clay suspensions. To investigate the effect of ion valence, sodium chloride (NaCl) and calcium chloride (CaCl$_2$) are used. For kaolin clay, the results show a CCC of 0.6mM NaCl ($\approx 0.04$ppt NaCl $=$ 0.04 PSU), and of 0.04mM CaCl$_2$ ($\approx 0.004$ppt CaCl$_2$). Because these salinities are lower than those commonly observed in nature, these findings indicate that kaolin clay should flocculate in nearly all natural aquatic environments. Furthermore, due to the fact that tap water often has salinities higher than this threshold, these results imply that great care is needed in experiments, especially in large facilities where using distilled water is not feasible. In addition, a simple criterion to estimate the CCC for a kaolin clay suspension is derived. This criterion predicts that flocculation occurs at extremely low salt concentrations and is approximately independent of clay concentration, in agreement with the experimental observations and consistent with experimental evidence from the literature.

physics.flu-dyn↗

arXiv2022

Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor

Liver cancer is one of the most common malignant diseases in the world. Segmentation and labeling of liver tumors and blood vessels in CT images can provide convenience for doctors in liver tumor diagnosis and surgical intervention. In the past decades, many state-of-the-art medical image segmentation algorithms appeared during this period. With the development of embedded devices, embedded deployment for medical segmentation and automatic reconstruction brings prospects for future automated surgical tasks. Yet, most of the existing segmentation methods mostly care about the spatial feature context and have a perception defect in the semantic relevance of medical images, which significantly affects the segmentation accuracy of liver tumors and blood vessels. Deploying large and complex models into embedded devices requires a reasonable trade-off between model accuracy, reasoning speed and model capacity. Given these problems, we introduce a multi-scale feature fusion network called TransFusionNet based on Transformer. This network achieved very competitive performance for liver vessel and liver tumor segmentation tasks, meanwhile it can improve the recognition of morphologic margins of liver tumors by exploiting the global information of CT images. Experiments show that in vessel segmentation task TransFusionNet achieved mean Dice coefficients of 0.899 and in liver tumor segmentation task TransFusionNet achieved mean Dice coefficients of 0.961. Compared with the state-of-the-art framework, our model achieves the best segmentation result. In addition, we deployed the model into an embedded micro-structure and constructed an integrated model for liver tumor vascular segmentation and reconstruction. This proprietary structure will be the exclusive component of the future medical field.

eess.IV↗

arXiv2021

Quantum phase modulation with acoustic cavities and quantum dots

Fast, efficient, and low power modulation of light at microwave frequencies is crucial for chip-scale classical and quantum processing as well as for long-range networks of superconducting quantum processors. A successful approach to bridge the gap between microwave and optical photons has been to use intermediate platforms such as acoustic waves, which can couple efficiently to a variety of quantum systems. Here, we use gigahertz-frequency focusing surface acoustic wave cavities on GaAs that are piezo-electrically coupled to superconducting circuits and parametrically coupled, via strain, to photons scattered from InAs quantum dots . We demonstrate strong modulation of single photons with a half-wave voltage as low as 44 mV, and subnatural modulation sideband linewidths. These demonstrations pave the way for efficient and low-noise transduction of quantum information between microwave and optical domains.

quant-ph↗

arXiv2021

Convergence of Gradient Algorithms for Nonconvex C^{1+alpha} Cost Functions

This paper is concerned with convergence of stochastic gradient algorithms with momentum terms in the nonconvex setting. A class of stochastic momentum methods, including stochastic gradient descent, heavy ball, and Nesterov's accelerated gradient, is analyzed in a general framework under mild assumptions. Based on the convergence result of expected gradients, we prove the almost sure convergence by a detailed discussion of the effects of momentum and the number of upcrossings. It is worth noting that there are not additional restrictions imposed on the objective function and stepsize. Another improvement over previous results is that the existing Lipschitz condition of the gradient is relaxed into the condition of Holder continuity. As a byproduct, we apply a localization procedure to extend our results to stochastic stepsizes.

math.OC↗

arXiv2021

Verdi: Quality Estimation and Error Detection for Bilingual Corpora

Translation Quality Estimation is critical to reducing post-editing efforts in machine translation and to cross-lingual corpus cleaning. As a research problem, quality estimation (QE) aims to directly estimate the quality of translation in a given pair of source and target sentences, and highlight the words that need corrections, without referencing to golden translations. In this paper, we propose Verdi, a novel framework for word-level and sentence-level post-editing effort estimation for bilingual corpora. Verdi adopts two word predictors to enable diverse features to be extracted from a pair of sentences for subsequent quality estimation, including a transformer-based neural machine translation (NMT) model and a pre-trained cross-lingual language model (XLM). We exploit the symmetric nature of bilingual corpora and apply model-level dual learning in the NMT predictor, which handles a primal task and a dual task simultaneously with weight sharing, leading to stronger context prediction ability than single-direction NMT models. By taking advantage of the dual learning scheme, we further design a novel feature to directly encode the translated target information without relying on the source context. Extensive experiments conducted on WMT20 QE tasks demonstrate that our method beats the winner of the competition and outperforms other baseline methods by a great margin. We further use the sentence-level scores provided by Verdi to clean a parallel corpus and observe benefits on both model performance and training efficiency.

cs.CL↗

arXiv2021

ByteSGAN: A Semi-supervised Generative Adversarial Network for Encrypted Traffic Classification of SDN Edge Gateway in Green Communication Network

With the rapid development of Green Communication Network, the types and quantity of network traffic data are accordingly increasing. Network traffic classification become a non-trivial research task in the area of network management and security, which not only help to improve the fine-grained network resource allocation, but also enable policy-driven network management. Meanwhile, the combination of SDN and Edge Computing can leverage both SDN at its global visiability of network-wide and Edge Computing at its low latency and good privacy-preserving. However, capturing large labeled datasets is a cumbersome and time-consuming manual labor. Semi-Supervised learning is an appropriate technique to overcome this problem. With that in mind, we proposed a Generative Adversarial Network (GAN)-based Semi-Supervised Learning Encrypted Traffic Classification method called \emph{ByteSGAN} embedded in SDN Edge Gateway to achieve the goal of traffic classification in a fine-grained manner to further improve network resource utilization. ByteSGAN can only use a small number of labeled traffic samples and a large number of unlabeled samples to achieve a good performance of traffic classification by modifying the structure and loss function of the regular GAN discriminator network in a semi-supervised learning way. Based on public dataset 'ISCX2012 VPN-nonVPN', two experimental results show that the ByteSGAN can efficiently improve the performance of traffic classifier and outperform the other supervised learning method like CNN.

cs.CR↗