Search arXiv⌕ Search

arXiv subjects

Hao Huang

Publications and source records attributed to Hao Huang.

At least 181 records · Page 10Linked to original sources

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↗

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↗

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↗

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↗

Design and Evaluation of A Cyber-Physical Resilient Power System Testbed

A power system is a complex cyber-physical system whose security is critical to its function. A major challenge is to model and analyze its communication pathways with respect to cyber threats. To achieve this, the design and evaluation of a cyber-physical power system (CPPS) testbed called Resilient Energy Systems Lab (RESLab) is presented that captures realistic cyber, physical, and protection system features. RESLab is architected to be a fundamental tool for studying and improving the resilience of complex CPPS to cyber threats. The cyber network is emulated using Common Open Research Emulator (CORE) that acts as a gateway for the physical and protection devices to communicate. The physical grid is simulated in the dynamic time frame using PowerWorld Dynamic Studio (PWDS). The protection components are modeled with both PWDS and physical devices including the SEL Real-Time Automation Controller (RTAC). Distributed Network Protocol 3 (DNP3) is used to monitor and control the grid. Then, exemplifying the design and validation of these tools, this paper presents four case studies on cyber-attack and defense using RESLab, where we demonstrate false data and command injection using Man-in-the-Middle and Denial of Service attacks and validate them on a large-scale synthetic electric grid.

eess.SY↗

Enriching Under-Represented Named-Entities To Improve Speech Recognition Performance

Automatic speech recognition (ASR) for under-represented named-entity (UR-NE) is challenging due to such named-entities (NE) have insufficient instances and poor contextual coverage in the training data to learn reliable estimates and representations. In this paper, we propose approaches to enriching UR-NEs to improve speech recognition performance. Specifically, our first priority is to ensure those UR-NEs to appear in the word lattice if there is any. To this end, we make exemplar utterances for those UR-NEs according to their categories (e.g. location, person, organization, etc.), ending up with an improved language model (LM) that boosts the UR-NE occurrence in the word lattice. With more UR-NEs appearing in the lattice, we then boost the recognition performance through lattice rescoring methods. We first enrich the representations of UR-NEs in a pre-trained recurrent neural network LM (RNNLM) by borrowing the embedding representations of the rich-represented NEs (RR-NEs), yielding the lattices that statistically favor the UR-NEs. Finally, we directly boost the likelihood scores of the utterances containing UR-NEs and gain further performance improvement.

cs.SD↗

The NTU-AISG Text-to-speech System for Blizzard Challenge 2020

We report our NTU-AISG Text-to-speech (TTS) entry systems for the Blizzard Challenge 2020 in this paper. There are two TTS tasks in this year's challenge, one is a Mandarin TTS task, the other is a Shanghai dialect TTS task. We have participated both. One of the main challenges is to build TTS systems with low-resource constraints, particularly for the case of Shanghai dialect, of which about three hours data are available to participants. To overcome the constraint, we adopt an average-speaker modeling method. That is, we first employ external Mandarin data to train both End-to-end acoustic model and WaveNet vocoder, then we use Shanghai dialect to tune the acoustic model and WaveNet vocoder respectively. Apart from this, we have no Shanghai dialect lexicon despite syllable transcripts are provided for the training data. Since we are not sure if similar syllable transcripts are provided for the evaluation data during the training stage, we use Mandarin lexicon for Shanghai dialect instead. With the letter, as decomposed from the corresponding Mandarin syllable, as input, though the naturalness and original speaker similarity of the synthesized speech are good, subjective evaluation results indicate the intelligibility of the synthesized speech is deeply undermined for the Shanghai dialect TTS system.

eess.AS↗

3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence

Point signature, a representation describing the structural neighborhood of a point in 3D shapes, can be applied to establish correspondences between points in 3D shapes. Conventional methods apply a weight-sharing network, e.g., any kind of graph neural networks, across all neighborhoods to directly generate point signatures and gain the generalization ability by extensive training over a large amount of training samples from scratch. However, these methods lack the flexibility in rapidly adapting to unseen neighborhood structures and thus generalizes poorly on new point sets. In this paper, we propose a novel meta-learning based 3D point signature model, named 3Dmetapointsignature (MEPS) network, that is capable of learning robust point signatures in 3D shapes. By regarding each point signature learning process as a task, our method obtains an optimized model over the best performance on the distribution of all tasks, generating reliable signatures for new tasks, i.e., signatures of unseen point neighborhoods. Specifically, the MEPS consists of two modules: a base signature learner and a meta signature learner. During training, the base-learner is trained to perform specific signature learning tasks. In the meantime, the meta-learner is trained to update the base-learner with optimal parameters. During testing, the meta-learner that is learned with the distribution of all tasks can adaptively change parameters of the base-learner, accommodating to unseen local neighborhoods. We evaluate the MEPS model on two datasets, e.g., FAUST and TOSCA, for dense 3Dshape correspondence. Experimental results demonstrate that our method not only gains significant improvements over the baseline model and achieves state-of-the-art results, but also is capable of handling unseen 3D shapes.

cs.CV↗

RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion

Many graph embedding approaches have been proposed for knowledge graph completion via link prediction. Among those, translating embedding approaches enjoy the advantages of light-weight structure, high efficiency and great interpretability. Especially when extended to complex vector space, they show the capability in handling various relation patterns including symmetry, antisymmetry, inversion and composition. However, previous translating embedding approaches defined in complex vector space suffer from two main issues: 1) representing and modeling capacities of the model are limited by the translation function with rigorous multiplication of two complex numbers; and 2) embedding ambiguity caused by one-to-many relations is not explicitly alleviated. In this paper, we propose a relation-adaptive translation function built upon a novel weighted product in complex space, where the weights are learnable, relation-specific and independent to embedding size. The translation function only requires eight more scalar parameters each relation, but improves expressive power and alleviates embedding ambiguity problem. Based on the function, we then present our Relation-adaptive translating Embedding (RatE) approach to score each graph triple. Moreover, a novel negative sampling method is proposed to utilize both prior knowledge and self-adversarial learning for effective optimization. Experiments verify RatE achieves state-of-the-art performance on four link prediction benchmarks.

cs.CL↗

Monolingual Data Selection Analysis for English-Mandarin Hybrid Code-switching Speech Recognition

In this paper, we conduct data selection analysis in building an English-Mandarin code-switching (CS) speech recognition (CSSR) system, which is aimed for a real CSSR contest in China. The overall training sets have three subsets, i.e., a code-switching data set, an English (LibriSpeech) and a Mandarin data set respectively. The code-switching data are Mandarin dominated. First of all, it is found using the overall data yields worse results, and hence data selection study is necessary. Then to exploit monolingual data, we find data matching is crucial. Mandarin data is closely matched with the Mandarin part in the code-switching data, while English data is not. However, Mandarin data only helps on those utterances that are significantly Mandarin-dominated. Besides, there is a balance point, over which more monolingual data will divert the CSSR system, degrading results. Finally, we analyze the effectiveness of combining monolingual data to train a CSSR system with the HMM-DNN hybrid framework. The CSSR system can perform within-utterance code-switch recognition, but it still has a margin with the one trained on code-switching data.

eess.AS↗

Robust Image Matching By Dynamic Feature Selection

Estimating dense correspondences between images is a long-standing image under-standing task. Recent works introduce convolutional neural networks (CNNs) to extract high-level feature maps and find correspondences through feature matching. However,high-level feature maps are in low spatial resolution and therefore insufficient to provide accurate and fine-grained features to distinguish intra-class variations for correspondence matching. To address this problem, we generate robust features by dynamically selecting features at different scales. To resolve two critical issues in feature selection,i.e.,how many and which scales of features to be selected, we frame the feature selection process as a sequential Markov decision-making process (MDP) and introduce an optimal selection strategy using reinforcement learning (RL). We define an RL environment for image matching in which each individual action either requires new features or terminates the selection episode by referring a matching score. Deep neural networks are incorporated into our method and trained for decision making. Experimental results show that our method achieves comparable/superior performance with state-of-the-art methods on three benchmarks, demonstrating the effectiveness of our feature selection strategy.

cs.CV↗

Gathering GitHub OSS Requirements from Q&A Community: an Empirical Study

Cross-community collaboration can exploit the expertise and knowledges of crowds in different communities. Recently increasing users in open source software (OSS) community like GitHub attempt to gather software requirements from question and answer (Q&A) communities such as Stack Overflow (SO). In order to investigate this emerging crosscommunity collaboration phenomenon, the paper presents an exploratory study on cross-community requirements gathering of OSS projects in GitHub. We manually sample 3266 practice cases and quantitatively analyze the popularity of the phenomenon, the characteristics of the gathered requirements, and collaboration behaviors of cross-community. Some important findings are obtained: more than half of the requirements gathered from SO are enhancements and the majority of the gathered requirements arenon-functionalrequirements.Inaddition,OSSdeveloperscan directlyobtainrelatedsolutionsandcontributionsofthegathered requirements from SO in the gathering process.

cs.SE↗

Generalized Contingency Analysis Based on Graph Theory and Line Outage Distribution Factor

Identifying the multiple critical components in power systems whose absence together has severe impact on system performance is a crucial problem for power systems known as (N-x) contingency analysis. However, the inherent combinatorial feature of the N-x contingency analysis problem incurs by the increase of x in the (N-x) term, making the problem intractable for even relatively small test systems. We present a new framework for identifying the N-x contingencies that captures both topology and physics of the network. Graph theory provides many ways to measure power grid graphs, i.e. buses as nodes and lines as edges, allowing researchers to characterize system structure and optimize algorithms. This paper proposes a scalable approach based on the group betweenness centrality (GBC) concept that measures the impact of multiple components in the electric power grid as well as line outage distribution factors (LODFs) that find the lines whose loss has the highest impact on the power flow in the network. The proposed approach is a quick and efficient solution for identifying the most critical lines in power networks. The proposed approach is validated using various test cases, and results show that the proposed approach is able to quickly identify multiple contingencies that result in violations.

math.OC↗

Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech

Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre. In this paper, we propose approaches to improving accent conversion applicability, as well as quality. First of all, we assume no reference speech is available at the conversion stage, and hence we employ an end-to-end text-to-speech system that is trained on native speech to generate native reference speech. To improve the quality and accent of the converted speech, we introduce reference encoders which make us capable of utilizing multi-source information. This is motivated by acoustic features extracted from native reference and linguistic information, which are complementary to conventional phonetic posteriorgrams (PPGs), so they can be concatenated as features to improve a baseline system based only on PPGs. Moreover, we optimize model architecture using GMM-based attention instead of windowed attention to elevate synthesized performance. Experimental results indicate when the proposed techniques are applied the integrated system significantly raises the scores of acoustic quality (30$\%$ relative increase in mean opinion score) and native accent (68$\%$ relative preference) while retaining the voice identity of the non-native speaker.

cs.CL↗

Approaches to Improving Recognition of Underrepresented Named Entities in Hybrid ASR Systems

In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance. The underrepresented words correspond to rare or out-of-vocabulary (OOV) words in the training data, and thereby can't be modeled reliably. We begin with graphemic lexicon which allows to drop the necessity of phonetic models in hybrid ASR. We study it under different settings and demonstrate its effectiveness in dealing with underrepresented NEs. Next, we study the impact of neural language model (LM) with letter-based features derived to handle infrequent words. After that, we attempt to enrich representations of underrepresented NEs in pretrained neural LM by borrowing the embedding representations of rich-represented words. This let us gain significant performance improvement on underrepresented NE recognition. Finally, we boost the likelihood scores of utterances containing NEs in the word lattices rescored by neural LMs and gain further performance improvement. The combination of the aforementioned approaches improves NE recognition by up to 42% relatively.

eess.AS↗

On local Turán problems

Since its formulation, Turán's hypergraph problems have been among the most challenging open problems in extremal combinatorics. One of them is the following: given a $3$-uniform hypergraph $\mathcal{F}$ on $n$ vertices in which any five vertices span at least one edge, prove that $|\mathcal{F}| \ge (1/4 -o(1))\binom{n}{3}$. The construction showing that this bound would be best possible is simply $\binom{X}{3} \cup \binom{Y}{3}$ where $X$ and $Y$ evenly partition the vertex set. This construction has the following more general $(2p+1, p+1)$-property: any set of $2p+1$ vertices spans a complete sub-hypergraph on $p+1$ vertices. One of our main results says that, quite surprisingly, for all $p>2$ the $(2p+1,p+1)$-property implies the conjectured lower bound.

math.CO↗

Dirac Fermions in Antiferromagnetic FeSn Kagome Lattices with Combined Space Inversion and Time Reversal Symmetry

Symmetry principles play a critical role in formulating the fundamental laws of nature, with a large number of symmetry-protected topological states identified in recent studies of quantum materials. As compelling examples, massless Dirac fermions are jointly protected by the space inversion symmetry $P$ and time reversal symmetry $T$ supplemented by additional crystalline symmetry, while evolving into Weyl fermions when either $P$ or $T$ is broken. Here, based on first-principles calculations, we reveal that massless Dirac fermions are present in a layered FeSn crystal containing antiferromagnetically coupled ferromagnetic Fe kagome layers, where each of the $P$ and $T$ symmetries is individually broken but the combined $PT$ symmetry is preserved. These stable Dirac fermions protected by the combined $PT$ symmetry with additional non-symmorphic $S_{\rm{2z}}$ symmetry can be transformed to either massless/massive Weyl or massive Dirac fermions by breaking the $PT$ or $S_{\rm{2z}}$ symmetry. Our angle-resolved photoemission spectroscopy experiments indeed observed the Dirac states in the bulk and two-dimensional Weyl-like states at the surface. The present study substantially enriches our fundamental understanding of the intricate connections between symmetries and topologies of matter, especially with the spin degree of freedom playing a vital role.

cond-mat.mtrl-sci↗

Precise tuning of the superconducting properties of Mn-doped Al films for transition edge sensors by ion-implantation

Magnetic impurities in metallic superconductors are important for both fundamental and applied sciences. In this study, we focused on dilute Mn-doped aluminum (AlMn) films, which are common superconducting materials used to make transition edge sensors (TES). We developed a multi-energy ion-implantation technique to make AlMn films. Compared with frequently used sputtering techniques, ion-implantation provides more precise and reliable control of the Mn doping concentration in the AlMn films.The ion implantation also enables us to quantitatively analyze the superconducting transition temperature curve as a function of the Mn doping concentration. We found that Mn dopants act as magnetic impurities and suppression of superconductivity is counteracted by the antiferromagnetic Ruderman Kittel Kasuya Yosida interaction among Mn dopants. The RKKY interaction can be tuned through defect engineering in the ion-implantation process and through post-implantation annealing.

cond-mat.mtrl-sci↗