arXiv subjects

Hao Huang

Publications and source records attributed to Hao Huang.

At least 163 records · Page 9Linked to original sources

arXiv2021

Part-X: A Family of Stochastic Algorithms for Search-Based Test Generation with Probabilistic Guarantees

Requirements driven search-based testing (also known as falsification) has proven to be a practical and effective method for discovering erroneous behaviors in Cyber-Physical Systems. Despite the constant improvements on the performance and applicability of falsification methods, they all share a common characteristic. Namely, they are best-effort methods which do not provide any guarantees on the absence of erroneous behaviors (falsifiers) when the testing budget is exhausted. The absence of finite time guarantees is a major limitation which prevents falsification methods from being utilized in certification procedures. In this paper, we address the finite-time guarantees problem by developing a new stochastic algorithm. Our proposed algorithm not only estimates (bounds) the probability that falsifying behaviors exist, but also it identifies the regions where these falsifying behaviors may occur. We demonstrate the applicability of our approach on standard benchmark functions from the optimization literature and on the F16 benchmark problem.

cs.LG↗

arXiv2021

Minimum word error training for non-autoregressive Transformer-based code-switching ASR

Non-autoregressive end-to-end ASR framework might be potentially appropriate for code-switching recognition task thanks to its inherent property that present output token being independent of historical ones. However, it still under-performs the state-of-the-art autoregressive ASR frameworks. In this paper, we propose various approaches to boosting the performance of a CTC-mask-based nonautoregressive Transformer under code-switching ASR scenario. To begin with, we attempt diversified masking method that are closely related with code-switching point, yielding an improved baseline model. More importantly, we employ MinimumWord Error (MWE) criterion to train the model. One of the challenges is how to generate a diversified hypothetical space, so as to obtain the average loss for a given ground truth. To address such a challenge, we explore different approaches to yielding desired N-best-based hypothetical space. We demonstrate the efficacy of the proposed methods on SEAME corpus, a challenging English-Mandarin code-switching corpus for Southeast Asia community. Compared with the crossentropy-trained strong baseline, the proposed MWE training method achieves consistent performance improvement on the test sets.

eess.AS↗

arXiv2021

Scattering-coded elastic meta-boundary

Object localization through active elastic waves is a crucial technology, but generally requires a transducer array with complex hardware. Although computational sensing has been demonstrated to be able to overcome the short-comings of transducer array by merging artificially designed structures into sensing process, coding spatial elastic waves for active object identification is still a knowledge gap. Here we propose a scattering-coded elastic meta-boundary composed of randomly distributed scatterers for computational identification of objects with a single transducer. The multiple scattering effect of the meta-boundary introduces complexity into scattered fields to achieve a highly uncorrelated scattering coding of elastic waves, thereby eliminating the ambiguity of the object location information. We demonstrate that the locations of objects can be uniquely identified by using the scattering coding of our designed meta-boundary, delivering a design of meta-boundary touchscreen for human-machine interaction. The proposed scattering-coded meta-boundary opens up avenues for artificially designed boundaries with the capability of information coding and identification, and may provide important applications in wave sensing, such as structural monitoring, underwater detection, indoor localization, and biomedical imaging.

physics.app-ph↗

arXiv2021

Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond

Conventional deformable registration methods aim at solving an optimization model carefully designed on image pairs and their computational costs are exceptionally high. In contrast, recent deep learning based approaches can provide fast deformation estimation. These heuristic network architectures are fully data-driven and thus lack explicit geometric constraints, e.g., topology-preserving, which are indispensable to generate plausible deformations. We design a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation in order to integrate advantages and avoid limitations of these two categories of approaches. Specifically, we introduce a generic optimization model to formulate diffeomorphic registration and develop a series of learnable architectures to obtain propagative updating in the coarse-to-fine feature space. Moreover, we propose a novel bilevel self-tuned training strategy, allowing efficient search of task-specific hyper-parameters. This training strategy increases the flexibility to various types of data while reduces computational and human burdens. We conduct two groups of image registration experiments on 3D volume datasets including image-to-atlas registration on brain MRI data and image-to-image registration on liver CT data. Extensive results demonstrate the state-of-the-art performance of the proposed method with diffeomorphic guarantee and extreme efficiency. We also apply our framework to challenging multi-modal image registration, and investigate how our registration to support the down-streaming tasks for medical image analysis including multi-modal fusion and image segmentation.

cs.CV↗

arXiv2021

3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation

With the popularity of 3D sensors in self-driving and other robotics applications, extensive research has focused on designing novel neural network architectures for accurate 3D point cloud completion. However, unlike in point cloud classification and reconstruction, the role of adversarial samples in3D point cloud completion has seldom been explored. In this work, we show that training with adversarial samples can improve the performance of neural networks on 3D point cloud completion tasks. We propose a novel approach to generate adversarial samples that benefit both the performance of clean and adversarial samples. In contrast to the PGD-k attack, our method generates adversarial samples that keep the geometric features in clean samples and contain few outliers. In particular, we use principal directions to constrain the adversarial perturbations for each input point. The gradient components in the mean direction of principal directions are taken as adversarial perturbations. In addition, we also investigate the effect of using the minimum curvature direction. Besides, we adopt attack strength accumulation and auxiliary Batch Normalization layers method to speed up the training process and alleviate the distribution mismatch between clean and adversarial samples. Experimental results show that training with the adversarial samples crafted by our method effectively enhances the performance of PCN on the ShapeNet dataset.

cs.CV↗

arXiv2021

Toward Efficient Wide-Area Identification of Multiple Element Contingencies in Power Systems

Power system N-x contingency analysis has inherent challenges due to its combinatorial characteristic where outages grow exponentially with the increase of x and N. To address these challenges, this paper proposes a method that utilizes Line Outage Distribution Factors (LODFs) and group betweenness centrality to identify subsets of critical branches. The proposed LODF metrics are used to select the high-impact branches. Based on each selected branch, the approach constructs the subgraph with parameters of distance and search level, while using branches' LODF metrics as the weights. A key innovation of this work is the use of the distance and search level parameters, which allow the subgraph to identify the most coupled critical elements that may be far away from a selected branch. The proposed approach is validated using the 200- and 500-bus test cases, and results show that the proposed approach can identify multiple N-x contingencies that cause violations.

eess.SY↗

arXiv2021

Mixed-Integer Optimization for Bio-Inspired Robust Power Network Design

Power systems are susceptible to natural threats including hurricanes and floods. Modern power grids are also increasingly threatened by cyber attacks. Existing approaches that help improve power system security and resilience may not be sufficient; this is evidenced by the continued challenge to supply energy to all customers during severe events. This paper presents an approach to address this challenge through bio-inspired power system network design to improve system reliability and resilience against disturbances. Inspired by naturally robust ecosystems, this paper considers the optimal ecological robustness that recognizes a unique balance between pathway efficiency and redundancy to ensure the survivability against disruptive events for given networks. This paper presents an approach that maximizes ecological robustness in transmission network design by formulating a mixed-integer nonlinear programming optimization problem with power system constraints. The results show the increase of the optimized power system's robustness and the improved reliability with less violations under N-x contingencies.

eess.SY↗

arXiv2021

Considerations in the Automatic Development of Electric Grid Restoration Plans

Power system restoration is a highly complex task that must be performed in a timely manner following a blackout. It is crucial to have the capability of developing a reliable restoration plan that can be adjusted quickly to different system conditions. This paper introduces a framework of an automated process that creates a restoration plan for a given power system. The required input includes the original system data under normal operating conditions and the status of the resources in the system that can be used for restoration. With a set of criteria to select as an option, the presented process can produce a restoration sequence in terms of which generator, load, branches, and breakers to close until a stopping criterion is met. The algorithm of the restoration process is described, and its application to a synthetic 200-bus case provides a restoration sequence from blackstart generating units to critical loads first and then to the rest of the system without violating any limits for frequency, voltage and branch loading.

eess.SY↗

arXiv2021

Real-time Power System Simulation with Hardware Devices through DNP3 in Cyber-Physical Testbed

Modern power grids are dependent on communication systems for data collection, visualization, and control. Distributed Network Protocol 3 (DNP3) is commonly used in supervisory control and data acquisition (SCADA) systems in power systems to allow control system software and hardware to communicate. To study the dependencies between communication network security, power system data collection, and industrial hardware, it is important to enable communication capabilities with real-time power system simulation. In this paper, we present the integration of new functionality of a power systems dynamic simulation package into our cyber-physical power system testbed that supports real-time power system data transfer using DNP3, demonstrated with an industrial real-time automation controller (RTAC). The usage and configuration of DNP3 with real-world equipment in to achieve power system monitoring and control of a large-scale synthetic electric grid via this DNP3 communication is presented. Then, an exemplar of DNP3 data collection and control is achieved in software and hardware using the 2000-bus Texas synthetic grid.

eess.SY↗

arXiv2021

Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment

Non-linear (large) time warping is a challenging source of nuisance in time-series analysis. In this paper, we propose a novel diffeomorphic temporal transformer network for both pairwise and joint time-series alignment. Our ResNet-TW (Deep Residual Network for Time Warping) tackles the alignment problem by compositing a flow of incremental diffeomorphic mappings. Governed by the flow equation, our Residual Network (ResNet) builds smooth, fluid and regular flows of velocity fields and consequently generates smooth and invertible transformations (i.e. diffeomorphic warping functions). Inspired by the elegant Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework, the final transformation is built by the flow of time-dependent vector fields which are none other than the building blocks of our Residual Network. The latter is naturally viewed as an Eulerian discretization schema of the flow equation (an ODE). Once trained, our ResNet-TW aligns unseen data by a single inexpensive forward pass. As we show in experiments on both univariate (84 datasets from UCR archive) and multivariate time-series (MSR Action-3D, Florence-3D and MSR Daily Activity), ResNet-TW achieves competitive performance in joint alignment and classification.

cs.CV↗

arXiv2021

G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation

Analyzing the structure of proteins is a key part of understanding their functions and thus their role in biology at the molecular level. In addition, design new proteins in a methodical way is a major engineering challenge. In this work, we introduce a joint geometric-neural networks approach for comparing, deforming and generating 3D protein structures. Viewing protein structures as 3D open curves, we adopt the Square Root Velocity Function (SRVF) representation and leverage its suitable geometric properties along with Deep Residual Networks (ResNets) for a joint registration and comparison. Our ResNets handle better large protein deformations while being more computationally efficient. On top of the mathematical framework, we further design a Geometric Variational Auto-Encoder (G-VAE), that once trained, maps original, previously unseen structures, into a low-dimensional (latent) hyper-sphere. Motivated by the spherical structure of the pre-shape space, we naturally adopt the von Mises-Fisher (vMF) distribution to model our hidden variables. We test the effectiveness of our models by generating novel protein structures and predicting completions of corrupted protein structures. Experimental results show that our method is able to generate plausible structures, different from the structures in the training data.

cs.CV↗

arXiv2021

E2E-based Multi-task Learning Approach to Joint Speech and Accent Recognition

In this paper, we propose a single multi-task learning framework to perform End-to-End (E2E) speech recognition (ASR) and accent recognition (AR) simultaneously. The proposed framework is not only more compact but can also yield comparable or even better results than standalone systems. Specifically, we found that the overall performance is predominantly determined by the ASR task, and the E2E-based ASR pretraining is essential to achieve improved performance, particularly for the AR task. Additionally, we conduct several analyses of the proposed method. First, though the objective loss for the AR task is much smaller compared with its counterpart of ASR task, a smaller weighting factor with the AR task in the joint objective function is necessary to yield better results for each task. Second, we found that sharing only a few layers of the encoder yields better AR results than sharing the overall encoder. Experimentally, the proposed method produces WER results close to the best standalone E2E ASR ones, while it achieves 7.7% and 4.2% relative improvement over standalone and single-task-based joint recognition methods on test set for accent recognition respectively.

eess.AS↗

arXiv2021

Multilingual Approach to Joint Speech and Accent Recognition with DNN-HMM Framework

Human can recognize speech, as well as the peculiar accent of the speech simultaneously. However, present state-of-the-art ASR system can rarely do that. In this paper, we propose a multilingual approach to recognizing English speech, and related accent that speaker conveys using DNN-HMM framework. Specifically, we assume different accents of English as different languages. We then merge them together and train a multilingual ASR system. During decoding, we conduct two experiments. One is a monolingual ASR-based decoding, with the accent information embedded at phone level, realizing word-based accent recognition (AR), and the other is a multilingual ASR-based decoding, realizing an approximated utterance-based AR. Experimental results on an 8-accent English speech recognition show both methods can yield WERs close to the conventional ASR systems that completely ignore the accent, as well as desired AR accuracy. Besides, we conduct extensive analysis for the proposed method, such as transfer learning without-domain data exploitation, cross-accent recognition confusion, as well as characteristics of accented-word.

eess.AS↗

arXiv2021

Superconducting microstrip single-photon detector with system detection efficiency over 90% at 1550 nm

Generally, a superconducting nanowire single-photon detector (SNSPD) is composed of wires with a typical width of ~100 nm. Recent studies have found that superconducting strips with a micrometer-scale width can also detect single photons. Compared with the SNSPD, the superconducting microstrip single-photon detector (SMSPD) has smaller kinetic inductance, higher working current, and lower requirement in fabrication accuracy, providing potential applications in the development of ultra-large active area detectors. However, the study on SMSPD is still in its infancy, and the realization of its high-performance and practical use remains an opening question. This study demonstrates a NbN SMSPD with a saturated system detection efficiency (SDE) of ~92.2% at a dark count rate of ~200 cps, a polarization sensitivity of ~1.03, and a minimum timing jitter of ~48 ps, at the telecom wavelength of 1550 nm when coupled with a single mode fiber and operated at 0.84 K. Furthermore, the detector's SDE is over 70% when operated at a 2.1-K closed-cycle cryocooler.

physics.ins-det↗

arXiv2021

RPATTACK: Refined Patch Attack on General Object Detectors

Nowadays, general object detectors like YOLO and Faster R-CNN as well as their variants are widely exploited in many applications. Many works have revealed that these detectors are extremely vulnerable to adversarial patch attacks. The perturbed regions generated by previous patch-based attack works on object detectors are very large which are not necessary for attacking and perceptible for human eyes. To generate much less but more efficient perturbation, we propose a novel patch-based method for attacking general object detectors. Firstly, we propose a patch selection and refining scheme to find the pixels which have the greatest importance for attack and remove the inconsequential perturbations gradually. Then, for a stable ensemble attack, we balance the gradients of detectors to avoid over-optimizing one of them during the training phase. Our RPAttack can achieve an amazing missed detection rate of 100% for both Yolo v4 and Faster R-CNN while only modifies 0.32% pixels on VOC 2007 test set. Our code is available at https://github.com/VDIGPKU/RPAttack.

cs.CV↗

arXiv2021

Man-in-The-Middle Attacks and Defense in a Power System Cyber-Physical Testbed

Man-in-The-Middle (MiTM) attacks present numerous threats to a smart grid. In a MiTM attack, an intruder embeds itself within a conversation between two devices to either eavesdrop or impersonate one of the devices, making it appear to be a normal exchange of information. Thus, the intruder can perform false data injection (FDI) and false command injection (FCI) attacks that can compromise power system operations, such as state estimation, economic dispatch, and automatic generation control (AGC). Very few researchers have focused on MiTM methods that are difficult to detect within a smart grid. To address this, we are designing and implementing multi-stage MiTM intrusions in an emulation-based cyber-physical power system testbed against a large-scale synthetic grid model to demonstrate how such attacks can cause physical contingencies such as misguided operation and false measurements. MiTM intrusions create FCI, FDI, and replay attacks in this synthetic power grid. This work enables stakeholders to defend against these stealthy attacks, and we present detection mechanisms that are developed using multiple alerts from intrusion detection systems and network monitoring tools. Our contribution will enable other smart grid security researchers and industry to develop further detection mechanisms for inconspicuous MiTM attacks.

cs.CR↗

arXiv2021

Multi-Source Data Fusion for Cyberattack Detection in Power Systems

Cyberattacks can cause a severe impact on power systems unless detected early. However, accurate and timely detection in critical infrastructure systems presents challenges, e.g., due to zero-day vulnerability exploitations and the cyber-physical nature of the system coupled with the need for high reliability and resilience of the physical system. Conventional rule-based and anomaly-based intrusion detection system (IDS) tools are insufficient for detecting zero-day cyber intrusions in the industrial control system (ICS) networks. Hence, in this work, we show that fusing information from multiple data sources can help identify cyber-induced incidents and reduce false positives. Specifically, we present how to recognize and address the barriers that can prevent the accurate use of multiple data sources for fusion-based detection. We perform multi-source data fusion for training IDS in a cyber-physical power system testbed where we collect cyber and physical side data from multiple sensors emulating real-world data sources that would be found in a utility and synthesizes these into features for algorithms to detect intrusions. Results are presented using the proposed data fusion application to infer False Data and Command injection-based Man-in- The-Middle (MiTM) attacks. Post collection, the data fusion application uses time-synchronized merge and extracts features followed by pre-processing such as imputation and encoding before training supervised, semi-supervised, and unsupervised learning models to evaluate the performance of the IDS. A major finding is the improvement of detection accuracy by fusion of features from cyber, security, and physical domains. Additionally, we observed the co-training technique performs at par with supervised learning methods when fed with our features.

cs.LG↗

arXiv2020

A 16-channel fiber array-coupled superconducting single-photon detector array with average system detection efficiency over 60% at telecom wavelength

We report a compact, scalable, and high-performance superconducting nanowire single-photon detector (SNSPD) array by using a multichannel optical fiber array-coupled configuration. For single pixels with an active area of 18 um in diameter and illuminated at the telecom wavelength of 1550 nm, we achieved a pixel yield of 13/16 on one chip, an average system detection efficiency of 69% at a dark count rate of 160 cps, a minimum timing jitter of 74 ps, and a maximum count rate of ~40 Mcps. The optical crosstalk coefficient between adjacent channels is better than -60 dB. The performance of the fiber array-coupled detectors is comparable with a standalone detector coupled to a single fiber. Our method is promising for the development of scalable, high-performance, and high-yield SNSPDs.

physics.ins-det↗