Searcharxiv⌕ Search

arXiv subjects

Hao Zhou

Publications and source records attributed to Hao Zhou.

At least 487 records · Page 27Linked to original sources
arXiv2018

DeepHTTP: Semantics-Structure Model with Attention for Anomalous HTTP Traffic Detection and Pattern Mining

In the Internet age, cyber-attacks occur frequently with complex types. Traffic generated by access activities can record website status and user request information, which brings a great opportunity for network attack detection. Among diverse network protocols, Hypertext Transfer Protocol (HTTP) is widely used in government, organizations and enterprises. In this work, we propose DeepHTTP, a semantics structure integration model utilizing Bidirectional Long Short-Term Memory (Bi-LSTM) with attention mechanism to model HTTP traffic as a natural language sequence. In addition to extracting traffic content information, we integrate structural information to enhance the generalization capabilities of the model. Moreover, the application of attention mechanism can assist in discovering critical parts of anomalous traffic and further mining attack patterns. Additionally, we demonstrate how to incrementally update the data set and retrain model so that it can be adapted to new anomalous traffic. Extensive experimental evaluations over large traffic data have illustrated that DeepHTTP has outstanding performance in traffic detection and pattern discovery.

cs.CR↗
arXiv2018

Deadline-Driven Multi-node Mobile Charging

Due to the merit without requiring charging cable, wireless power transfer technologies have drawn rising attention as a new method to replenish energy to Wireless Rechargeable Sensor Networks (WRSNs). In this paper, we study mobile charger scheduling problem for multi-node recharging with deadline-series. Our target is to maximize the overall effective charging utility, and minimize the traveling time as well. Instead of charging only once over a scheduling cycle, we incorporate the multiple charging strategy for multi-node charging with deadline constraint, where charging spots and tour are jointly optimized. Specifically, we formulate the effective charging utility maximization problem as to maximize a monotone submodular function subject to a partition matroid constraint, and propose a simple but effective 1/2 -approximation greedy algorithm. After that, we present the grid-based skip-substitute operation further to save the traveling time, which can increase the charging utility. Finally, we conduct the evaluation for the performance of our scheduling scheme. Comparing to the Early Deadline First scheme, the simulation and field experiment results show that our algorithm outperform EDF by 37.5% and 37.9%, respectively.

cs.NI↗
arXiv2018

From Communication to Sensing : Recognizing and Counting Repetitive Motions with Wireless Backscattering

Recently several ground-breaking RF-based motion recognition systems were proposed to detect and/or recognize macro/micro human movements. These systems often suffer from various interferences caused by multiple-users moving simultaneously, resulting in extremely low recognition accuracy. To tackle this challenge, we propose a novel system, called Motion-Fi, which marries battery free wireless backscattering and device-free sensing. Motion-Fi is an accurate, interference tolerable motion-recognition system, which counts repetitive motions without using scenario-dependent templates or profiles and enables multi-users performing certain motions simultaneously because of the relatively short transmission range of backscattered signals. Although the repetitive motions are fairly well detectable through the backscattering signals in theory, in reality they get blended into various other system noises during the motion. Moreover, irregular motion patterns among users will lead to expensive computation cost for motion recognition. We build a backscattering wireless platform to validate our design in various scenarios for over 6 months when different persons, distances and orientations are incorporated. In our experiments, the periodicity in motions could be recognized without any learning or training process, and the accuracy of counting such motions can be achieved within 5% count error. With little efforts in learning the patterns, our method could achieve 93.1% motion-recognition accuracy for a variety of motions. Moreover, by leveraging the periodicity of motions, the recognition accuracy could be further improved to nearly 100% with only 3 repetitions. Our experiments also show that the motions of multiple persons separating by around 2 meters cause little accuracy reduction in the counting process.

eess.SP↗
arXiv2018

On Tree-Based Neural Sentence Modeling

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of different tree structures, we replace the parsing trees with trivial trees (i.e., binary balanced tree, left-branching tree and right-branching tree) in the encoders. Though trivial trees contain no syntactic information, those encoders get competitive or even better results on all of the ten downstream tasks we investigated. This surprising result indicates that explicit syntax guidance may not be the main contributor to the superior performances of tree-based neural sentence modeling. Further analysis show that tree modeling gives better results when crucial words are closer to the final representation. Additional experiments give more clues on how to design an effective tree-based encoder. Our code is open-source and available at https://github.com/ExplorerFreda/TreeEnc.

cs.CL↗
arXiv2018

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose Emotional Chatting Machine (ECM) that can generate appropriate responses not only in content (relevant and grammatical) but also in emotion (emotionally consistent). To the best of our knowledge, this is the first work that addresses the emotion factor in large-scale conversation generation. ECM addresses the factor using three new mechanisms that respectively (1) models the high-level abstraction of emotion expressions by embedding emotion categories, (2) captures the change of implicit internal emotion states, and (3) uses explicit emotion expressions with an external emotion vocabulary. Experiments show that the proposed model can generate responses appropriate not only in content but also in emotion.

cs.CL↗
arXiv2018

BRITS: Bidirectional Recurrent Imputation for Time Series

Time series are widely used as signals in many classification/regression tasks. It is ubiquitous that time series contains many missing values. Given multiple correlated time series data, how to fill in missing values and to predict their class labels? Existing imputation methods often impose strong assumptions of the underlying data generating process, such as linear dynamics in the state space. In this paper, we propose BRITS, a novel method based on recurrent neural networks for missing value imputation in time series data. Our proposed method directly learns the missing values in a bidirectional recurrent dynamical system, without any specific assumption. The imputed values are treated as variables of RNN graph and can be effectively updated during the backpropagation.BRITS has three advantages: (a) it can handle multiple correlated missing values in time series; (b) it generalizes to time series with nonlinear dynamics underlying; (c) it provides a data-driven imputation procedure and applies to general settings with missing data.We evaluate our model on three real-world datasets, including an air quality dataset, a health-care data, and a localization data for human activity. Experiments show that our model outperforms the state-of-the-art methods in both imputation and classification/regression accuracies.

cs.LG↗
arXiv2018

Augmenting End-to-End Dialog Systems with Commonsense Knowledge

Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent is expected to respond to human responses in an interesting and engaging way, commonsense knowledge has to be integrated into the model effectively. In this paper, we investigate the impact of providing commonsense knowledge about the concepts covered in the dialog. Our model represents the first attempt to integrating a large commonsense knowledge base into end-to-end conversational models. In the retrieval-based scenario, we propose the Tri-LSTM model to jointly take into account message and commonsense for selecting an appropriate response. Our experiments suggest that the knowledge-augmented models are superior to their knowledge-free counterparts in automatic evaluation.

cs.AI↗
arXiv2017

Modeling Past and Future for Neural Machine Translation

Existing neural machine translation systems do not explicitly model what has been translated and what has not during the decoding phase. To address this problem, we propose a novel mechanism that separates the source information into two parts: translated Past contents and untranslated Future contents, which are modeled by two additional recurrent layers. The Past and Future contents are fed to both the attention model and the decoder states, which offers NMT systems the knowledge of translated and untranslated contents. Experimental results show that the proposed approach significantly improves translation performance in Chinese-English, German-English and English-German translation tasks. Specifically, the proposed model outperforms the conventional coverage model in both of the translation quality and the alignment error rate.

cs.CL↗
arXiv2017

Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation

This paper addresses the question: Why do neural dialog systems generate short and meaningless replies? We conjecture that, in a dialog system, an utterance may have multiple equally plausible replies, causing the deficiency of neural networks in the dialog application. We propose a systematic way to mimic the dialog scenario in a machine translation system, and manage to reproduce the phenomenon of generating short and less meaningful sentences in the translation setting, showing evidence of our conjecture.

cs.CL↗
arXiv2017

Strongly Secure and Efficient Data Shuffle On Hardware Enclaves

Mitigating memory-access attacks on the Intel SGX architecture is an important and open research problem. A natural notion of the mitigation is cache-miss obliviousness which requires the cache-misses emitted during an enclave execution are oblivious to sensitive data. This work realizes the cache-miss obliviousness for the computation of data shuffling. The proposed approach is to software-engineer the oblivious algorithm of Melbourne shuffle on the Intel SGX/TSX architecture, where the Transaction Synchronization eXtension (TSX) is (ab)used to detect the occurrence of cache misses. In the system building, we propose software techniques to prefetch memory data prior to the TSX transaction to defend the physical bus-tapping attacks. Our evaluation based on real implementation shows that our system achieves superior performance and lower transaction abort rate than the related work in the existing literature.

cs.CR↗
arXiv2017

Dynamic Oracle for Neural Machine Translation in Decoding Phase

The past several years have witnessed the rapid progress of end-to-end Neural Machine Translation (NMT). However, there exists discrepancy between training and inference in NMT when decoding, which may lead to serious problems since the model might be in a part of the state space it has never seen during training. To address the issue, Scheduled Sampling has been proposed. However, there are certain limitations in Scheduled Sampling and we propose two dynamic oracle-based methods to improve it. We manage to mitigate the discrepancy by changing the training process towards a less guided scheme and meanwhile aggregating the oracle's demonstrations. Experimental results show that the proposed approaches improve translation quality over standard NMT system.

cs.CL↗
arXiv2017

A Deep Cascade Network for Unaligned Face Attribute Classification

Humans focus attention on different face regions when recognizing face attributes. Most existing face attribute classification methods use the whole image as input. Moreover, some of these methods rely on fiducial landmarks to provide defined face parts. In this paper, we propose a cascade network that simultaneously learns to localize face regions specific to attributes and performs attribute classification without alignment. First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) specific to attributes. Then multiple part-based networks and a whole-image-based network are separately constructed and combined together by the region switch layer and attribute relation layer for final attribute classification. A multi-net learning method and hint-based model compression is further proposed to get an effective localization model and a compact classification model, respectively. Our approach achieves significantly better performance than state-of-the-art methods on unaligned CelebA dataset, reducing the classification error by 30.9%.

cs.CV↗
arXiv2017

Probing Galactic Diffuse TeV Gamma-Ray Emission with the HAWC Observatory

Galactic diffuse TeV gamma-ray emission is produced by the interaction of high-energy cosmic-ray particles with matter and radiation in our Galaxy. The measurement of Galactic diffuse TeV gamma-ray emission would provide strong constraints on the acceleration and propagation of Galactic cosmic rays. The High Altitude Water Cherenkov (HAWC) Observatory, located in central Mexico at 4100 m above sea level, is sensitive to gamma rays between a few hundreds GeV and about 100 TeV. Thanks to its large field of view of 2 steradians and excellent background estimation, HAWC has a unique capability to observe large extended sources such as Galactic diffuse emission. We present the analysis strategy to detect the Galactic diffuse emission with HAWC, including techniques to remove contaminations from localized sources.

astro-ph.HE↗
arXiv2017

Constraining the Diffusion Coefficient with HAWC TeV Gamma-Ray Observations of Two Nearby Pulsar Wind Nebulae

Nearby electron/positron accelerators, mostly Pulsar Wind Nebulae (PWNe), have been proposed as potential origins of the positron excess above 10 GeV. The HAWC Observatory reveals two very extended sources spatially coincident with two nearby middle-aged pulsars: Geminga and PSR B0656+14, suggesting ultrarelativistic electrons/positrons accelerated in our backyard. Morphological studies on these two PWNe provide a constraint on the diffusion coefficient at HAWC energies. In this poster, we will present the model development and morphological studies on these PWNe, and the derived diffusion coefficient that best fits the data.

astro-ph.HE↗
arXiv2017

Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images

Lighting estimation from face images is an important task and has applications in many areas such as image editing, intrinsic image decomposition, and image forgery detection. We propose to train a deep Convolutional Neural Network (CNN) to regress lighting parameters from a single face image. Lacking massive ground truth lighting labels for face images in the wild, we use an existing method to estimate lighting parameters, which are treated as ground truth with unknown noises. To alleviate the effect of such noises, we utilize the idea of Generative Adversarial Networks (GAN) and propose a Label Denoising Adversarial Network (LDAN) to make use of synthetic data with accurate ground truth to help train a deep CNN for lighting regression on real face images. Experiments show that our network outperforms existing methods in producing consistent lighting parameters of different faces under similar lighting conditions. Moreover, our method is 100,000 times faster in execution time than prior optimization-based lighting estimation approaches.

cs.CV↗
arXiv2017

Chunk-Based Bi-Scale Decoder for Neural Machine Translation

In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we propose a new type of decoder for NMT, which splits the decode state into two parts and updates them in two different time-scales. Specifically, we first predict a chunk time-scale state for phrasal modeling, on top of which multiple word time-scale states are generated. In this way, the target sentence is translated hierarchically from chunks to words, with information in different granularities being leveraged. Experiments show that our proposed model significantly improves the translation performance over the state-of-the-art NMT model.

cs.CL↗
arXiv2017

Mesoscopic chaos mediated by Drude electron-hole plasma in silicon optomechanical oscillators

Chaos has revolutionized the field of nonlinear science and stimulated foundational studies from neural networks, extreme event statistics, to physics of electron transport. Recent studies in cavity optomechanics provide a new platform to uncover quintessential architectures of chaos generation and the underlying physics. Here we report the generation of dynamical chaos in silicon-based monolithic optomechanical oscillators, enabled by the strong and coupled nonlinearities of two-photon-absorption induced Drude electron-hole plasma. Deterministic chaotic oscillation is achieved, and statistical and entropic characterization quantifies the chaos complexity at 60 fJ intracavity energies. The correlation dimension D2 is determined at 1.67 for the chaotic attractor, along with maximal Lyapunov exponent rate about 2.94 the fundamental optomechanical oscillation for fast adjacent trajectory divergence. Nonlinear dynamical maps demonstrate the subharmonics, bifurcations, and stable regimes, along with distinct transitional routes into chaos. This provides a CMOS-compatible and scalable architecture for understanding complex dynamics on the mesoscopic scale.

physics.optics↗