PyTorchKR Papers

최신 논문

총 561편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1712.05929

A Machine Learning Framework for Resource Allocation Assisted by Cloud Computing

Conventionally, the resource allocation is formulated as an optimization problem and solved online with instantaneous scenario information. Since most resource allocation problems are not convex, the optimal solutions are very difficult to be obtained in real time. Lagrangian relaxation or greedy methods are then often employed, which results in performance loss. Therefore, the conventional methods of resource allocation are facing great challenges to meet the ever-increasing QoS requirements of users with scarce radio resource. Assisted by cloud computing, a huge amount of historical data on scenarios can be collected for extracting similarities among scenarios using machine learning. Moreover, optimal or near-optimal solutions of historical scenarios can be searched offline and stored in advance. When the measured data of current scenario arrives, the current scenario is compared with historical scenarios to find the most similar one. Then, the optimal or near-optimal solution in the most similar historical scenario is adopted to allocate the radio resources for the current scenario. To facilitate the application of new design philosophy, a machine learning framework is proposed for resource allocation assisted by cloud computing. An example of beam allocation in multi-user massive multiple-input-multiple-output (MIMO) systems shows that the proposed machine-learning based resource allocation outperforms conventional methods.

arXiv:1712.05914

Cyberattack Detection in Mobile Cloud Computing: A Deep Learning Approach

With the rapid growth of mobile applications and cloud computing, mobile cloud computing has attracted great interest from both academia and industry. However, mobile cloud applications are facing security issues such as data integrity, users' confidentiality, and service availability. A preventive approach to such problems is to detect and isolate cyber threats before they can cause serious impacts to the mobile cloud computing system. In this paper, we propose a novel framework that leverages a deep learning approach to detect cyberattacks in mobile cloud environment. Through experimental results, we show that our proposed framework not only recognizes diverse cyberattacks, but also achieves a high accuracy (up to 97.11%) in detecting the attacks. Furthermore, we present the comparisons with current machine learning-based approaches to demonstrate the effectiveness of our proposed solution.

arXiv:1712.06015

StackInsights: Cognitive Learning for Hybrid Cloud Readiness

Hybrid cloud is an integrated cloud computing environment utilizing a mix of public cloud, private cloud, and on-premise traditional IT infrastructures. Workload awareness, defined as a detailed full range understanding of each individual workload, is essential in implementing the hybrid cloud. While it is critical to perform an accurate analysis to determine which workloads are appropriate for on-premise deployment versus which workloads can be migrated to a cloud off-premise, the assessment is mainly performed by rule or policy based approaches. In this paper, we introduce StackInsights, a novel cognitive system to automatically analyze and predict the cloud readiness of workloads for an enterprise. Our system harnesses the critical metrics across the entire stack: 1) infrastructure metrics, 2) data relevance metrics, and 3) application taxonomy, to identify workloads that have characteristics of a) low sensitivity with respect to business security, criticality and compliance, and b) low response time requirements and access patterns. Since the capture of the data relevance metrics involves an intrusive and in-depth scanning of the content of storage objects, a machine learning model is applied to perform the business relevance classification by learning from the meta level metrics harnessed across stack. In contrast to traditional methods, StackInsights significantly reduces the total time for hybrid cloud readiness assessment by orders of magnitude.

arXiv:1710.05112

Video Classification With CNNs: Using The Codec As A Spatio-Temporal Activity Sensor

We investigate video classification via a two-stream convolutional neural network (CNN) design that directly ingests information extracted from compressed video bitstreams. Our approach begins with the observation that all modern video codecs divide the input frames into macroblocks (MBs). We demonstrate that selective access to MB motion vector (MV) information within compressed video bitstreams can also provide for selective, motion-adaptive, MB pixel decoding (a.k.a., MB texture decoding). This in turn allows for the derivation of spatio-temporal video activity regions at extremely high speed in comparison to conventional full-frame decoding followed by optical flow estimation. In order to evaluate the accuracy of a video classification framework based on such activity data, we independently train two CNN architectures on MB texture and MV correspondences and then fuse their scores to derive the final classification of each test video. Evaluation on two standard datasets shows that the proposed approach is competitive to the best two-stream video classification approaches found in the literature. At the same time: (i) a CPU-based realization of our MV extraction is over 977 times faster than GPU-based optical flow methods; (ii) selective decoding is up to 12 times faster than full-frame decoding; (iii) our proposed spatial and temporal CNNs perform inference at 5 to 49 times lower cloud computing cost than the fastest methods from the literature.

arXiv:1712.09795

Learning to Customize Network Security Rules

Security is a major concern for organizations who wish to leverage cloud computing. In order to reduce security vulnerabilities, public cloud providers offer firewall functionalities. When properly configured, a firewall protects cloud networks from cyber-attacks. However, proper firewall configuration requires intimate knowledge of the protected system, high expertise and on-going maintenance. As a result, many organizations do not use firewalls effectively, leaving their cloud resources vulnerable. In this paper, we present a novel supervised learning method, and prototype, which compute recommendations for firewall rules. Recommendations are based on sampled network traffic meta-data (NetFlow) collected from a public cloud provider. Labels are extracted from firewall configurations deemed to be authored by experts. NetFlow is collected from network routers, avoiding expensive collection from cloud VMs, as well as relieving privacy concerns. The proposed method captures network routines and dependencies between resources and firewall configuration. The method predicts IPs to be allowed by the firewall. A grouping algorithm is subsequently used to generate a manageable number of IP ranges. Each range is a parameter for a firewall rule. We present results of experiments on real data, showing ROC AUC of 0.92, compared to 0.58 for an unsupervised baseline. The results prove the hypothesis that firewall rules can be automatically generated based on router data, and that an automated method can be effective in blocking a high percentage of malicious traffic.

arXiv:1801.03984

A Brain-Inspired Trust Management Model to Assure Security in a Cloud based IoT Framework for Neuroscience Applications

Rapid popularity of Internet of Things (IoT) and cloud computing permits neuroscientists to collect multilevel and multichannel brain data to better understand brain functions, diagnose diseases, and devise treatments. To ensure secure and reliable data communication between end-to-end (E2E) devices supported by current IoT and cloud infrastructure, trust management is needed at the IoT and user ends. This paper introduces a Neuro-Fuzzy based Brain-inspired trust management model (TMM) to secure IoT devices and relay nodes, and to ensure data reliability. The proposed TMM utilizes node behavioral trust and data trust estimated using Adaptive Neuro-Fuzzy Inference System and weighted-additive methods respectively to assess the nodes trustworthiness. In contrast to the existing fuzzy based TMMs, the NS2 simulation results confirm the robustness and accuracy of the proposed TMM in identifying malicious nodes in the communication network. With the growing usage of cloud based IoT frameworks in Neuroscience research, integrating the proposed TMM into the existing infrastructure will assure secure and reliable data communication among the E2E devices.

arXiv:1801.08618

JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services

Deep learning models are being deployed in many mobile intelligent applications. End-side services, such as intelligent personal assistants, autonomous cars, and smart home services often employ either simple local models on the mobile or complex remote models on the cloud. However, recent studies have shown that partitioning the DNN computations between the mobile and cloud can increase the latency and energy efficiencies. In this paper, we propose an efficient, adaptive, and practical engine, JointDNN, for collaborative computation between a mobile device and cloud for DNNs in both inference and training phase. JointDNN not only provides an energy and performance efficient method of querying DNNs for the mobile side but also benefits the cloud server by reducing the amount of its workload and communications compared to the cloud-only approach. Given the DNN architecture, we investigate the efficiency of processing some layers on the mobile device and some layers on the cloud server. We provide optimization formulations at layer granularity for forward- and backward-propagations in DNNs, which can adapt to mobile battery limitations and cloud server load constraints and quality of service. JointDNN achieves up to 18 and 32 times reductions on the latency and mobile energy consumption of querying DNNs compared to the status-quo approaches, respectively.

arXiv:1802.03155

Web-Based Implementation of Travelling Salesperson Problem Using Genetic Algorithm

The world is connected through the Internet. As the abundance of Internet users connected into the Web and the popularity of cloud computing research, the need of Artificial Intelligence (AI) is demanding. In this research, Genetic Algorithm (GA) as AI optimization method through natural selection and genetic evolution is utilized. There are many applications of GA such as web mining, load balancing, routing, and scheduling or web service selection. Hence, it is a challenging task to discover whether the code mainly server side and web based language technology affects the performance of GA. Travelling Salesperson Problem (TSP) as Non Polynomial-hard (NP-hard) problem is provided to be a problem domain to be solved by GA. While many scientists prefer Python in GA implementation, another popular high-level interpreter programming language such as PHP (PHP Hypertext Preprocessor) and Ruby were benchmarked. Line of codes, file sizes, and performances based on GA implementation and runtime were found varies among these programming languages. Based on the result, the use of Ruby in GA implementation is recommended.

arXiv:1802.09957

Convolutional Neural Networks for Toxic Comment Classification

Flood of information is produced in a daily basis through the global Internet usage arising from the on-line interactive communications among users. While this situation contributes significantly to the quality of human life, unfortunately it involves enormous dangers, since on-line texts with high toxicity can cause personal attacks, on-line harassment and bullying behaviors. This has triggered both industrial and research community in the last few years while there are several tries to identify an efficient model for on-line toxic comment prediction. However, these steps are still in their infancy and new approaches and frameworks are required. On parallel, the data explosion that appears constantly, makes the construction of new machine learning computational tools for managing this information, an imperative need. Thankfully advances in hardware, cloud computing and big data management allow the development of Deep Learning approaches appearing very promising performance so far. For text classification in particular the use of Convolutional Neural Networks (CNN) have recently been proposed approaching text analytics in a modern manner emphasizing in the structure of words in a document. In this work, we employ this approach to discover toxic comments in a large pool of documents provided by a current Kaggle's competition regarding Wikipedia's talk page edits. To justify this decision we choose to compare CNNs against the traditional bag-of-words approach for text analysis combined with a selection of algorithms proven to be very effective in text classification. The reported results provide enough evidence that CNN enhance toxic comment classification reinforcing research interest towards this direction.

arXiv:1603.01581

Causal inference for data-driven debugging and decision making in cloud computing

Cloud computing involves complex technical and economical systems and interactions. This brings about various challenges, two of which are: (1) debugging and control to optimize the performance of computing systems, with the help of sandbox experiments, and (2) privacy-preserving prediction of the cost of ``spot'' resources for decision making of cloud clients. In this paper, we formalize debugging by counterfactual probabilities and control by post-(soft-)interventional probabilities. We prove that counterfactuals can approximately be calculated from a ``stochastic'' graphical causal model (while they are originally defined only for ``deterministic'' functional causal models), and based on this sketch a data-driven approach to address problem (1). To address problem (2), we formalize bidding by post-(soft-)interventional probabilities and present a simple mathematical result on approximate integration of ``incomplete'' conditional probability distributions. We show how this can be used by cloud clients to trade off privacy against predictability of the outcome of their bidding actions in a toy scenario. We report experiments on simulated and real data.

arXiv:1708.08127

RIOT: a Stochastic-based Method for Workflow Scheduling in the Cloud

Cloud computing provides engineers or scientists a place to run complex computing tasks. Finding a workflow's deployment configuration in a cloud environment is not easy. Traditional workflow scheduling algorithms were based on some heuristics, e.g. reliability greedy, cost greedy, cost-time balancing, etc., or more recently, the meta-heuristic methods, such as genetic algorithms. These methods are very slow and not suitable for rescheduling in the dynamic cloud environment. This paper introduces RIOT (Randomized Instance Order Types), a stochastic based method for workflow scheduling. RIOT groups the tasks in the workflow into virtual machines via a probability model and then uses an effective surrogate-based method to assess a large amount of potential scheduling. Experiments in dozens of study cases showed that RIOT executes tens of times faster than traditional methods while generating comparable results to other methods.

arXiv:1805.00331

Smart Surveillance as an Edge Network Service: from Harr-Cascade, SVM to a Lightweight CNN

Edge computing efficiently extends the realm of information technology beyond the boundary defined by cloud computing paradigm. Performing computation near the source and destination, edge computing is promising to address the challenges in many delay-sensitive applications, like real-time human surveillance. Leveraging the ubiquitously connected cameras and smart mobile devices, it enables video analytics at the edge. In recent years, many smart video surveillance approaches are proposed for object detection and tracking by using Artificial Intelligence (AI) and Machine Learning (ML) algorithms. This work explores the feasibility of two popular human-objects detection schemes, Harr-Cascade and HOG feature extraction and SVM classifier, at the edge and introduces a lightweight Convolutional Neural Network (L-CNN) leveraging the depthwise separable convolution for less computation, for human detection. Single Board computers (SBC) are used as edge devices for tests and algorithms are validated using real-world campus surveillance video streams and open data sets. The experimental results are promising that the final algorithm is able to track humans with a decent accuracy at a resource consumption affordable by edge devices in real-time manner.

arXiv:1805.01162

SafeRNet: Safe Transportation Routing in the era of Internet of Vehicles and Mobile Crowd Sensing

World wide road traffic fatality and accident rates are high, and this is true even in technologically advanced countries like the USA. Despite the advances in Intelligent Transportation Systems, safe transportation routing i.e., finding safest routes is largely an overlooked paradigm. In recent years, large amount of traffic data has been produced by people, Internet of Vehicles and Internet of Things (IoT). Also, thanks to advances in cloud computing and proliferation of mobile communication technologies, it is now possible to perform analysis on vast amount of generated data (crowd sourced) and deliver the result back to users in real time. This paper proposes SafeRNet, a safe route computation framework which takes advantage of these technologies to analyze streaming traffic data and historical data to effectively infer safe routes and deliver them back to users in real time. SafeRNet utilizes Bayesian network to formulate safe route model. Furthermore, a case study is presented to demonstrate the effectiveness of our approach using real traffic data. SafeRNet intends to improve drivers safety in a modern technology rich transportation system.

arXiv:1805.04754

Incremental Learning Framework Using Cloud Computing

High volume of data, perceived as either challenge or opportunity. Deep learning architecture demands high volume of data to effectively back propagate and train the weights without bias. At the same time, large volume of data demands higher capacity of the machine where it could be executed seamlessly. Budding data scientist along with many research professionals face frequent disconnection issue with cloud computing framework (working without dedicated connection) due to free subscription to the platform. Similar issues also visible while working on local computer where computer may run out of resource or power sometimes and researcher has to start training the models all over again. In this paper, we intend to provide a way to resolve this issue and progressively training the neural network even after having frequent disconnection or resource outage without loosing much of the progress

arXiv:1805.05098

Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks

Recently, Deep Learning (DL), especially Convolutional Neural Network (CNN), develops rapidly and is applied to many tasks, such as image classification, face recognition, image segmentation, and human detection. Due to its superior performance, DL-based models have a wide range of application in many areas, some of which are extremely safety-critical, e.g. intelligent surveillance and autonomous driving. Due to the latency and privacy problem of cloud computing, embedded accelerators are popular in these safety-critical areas. However, the robustness of the embedded DL system might be harmed by inserting hardware/software Trojans into the accelerator and the neural network model, since the accelerator and deploy tool (or neural network model) are usually provided by third-party companies. Fortunately, inserting hardware Trojans can only achieve inflexible attack, which means that hardware Trojans can easily break down the whole system or exchange two outputs, but can't make CNN recognize unknown pictures as targets. Though inserting software Trojans has more freedom of attack, it often requires tampering input images, which is not easy for attackers. So, in this paper, we propose a hardware-software collaborative attack framework to inject hidden neural network Trojans, which works as a back-door without requiring manipulating input images and is flexible for different scenarios. We test our attack framework for image classification and face recognition tasks, and get attack success rate of 92.6% and 100% on CIFAR10 and YouTube Faces, respectively, while keeping almost the same accuracy as the unattacked model in the normal mode. In addition, we show a specific attack scenario in which a face recognition system is attacked and gives a specific wrong answer.

arXiv:1805.07588

Robust Optimization over Multiple Domains

In this work, we study the problem of learning a single model for multiple domains. Unlike the conventional machine learning scenario where each domain can have the corresponding model, multiple domains (i.e., applications/users) may share the same machine learning model due to maintenance loads in cloud computing services. For example, a digit-recognition model should be applicable to hand-written digits, house numbers, car plates, etc. Therefore, an ideal model for cloud computing has to perform well at each applicable domain. To address this new challenge from cloud computing, we develop a framework of robust optimization over multiple domains. In lieu of minimizing the empirical risk, we aim to learn a model optimized to the adversarial distribution over multiple domains. Hence, we propose to learn the model and the adversarial distribution simultaneously with the stochastic algorithm for efficiency. Theoretically, we analyze the convergence rate for convex and non-convex models. To our best knowledge, we first study the convergence rate of learning a robust non-convex model with a practical algorithm. Furthermore, we demonstrate that the robustness of the framework and the convergence rate can be further enhanced by appropriate regularizers over the adversarial distribution. The empirical study on real-world fine-grained visual categorization and digits recognition tasks verifies the effectiveness and efficiency of the proposed framework.

arXiv:1805.07569

Reliable counting of weakly labeled concepts by a single spiking neuron model

Making an informed, correct and quick decision can be life-saving. It's crucial for animals during an escape behaviour or for autonomous cars during driving. The decision can be complex and may involve an assessment of the amount of threats present and the nature of each threat. Thus, we should expect early sensory processing to supply classification information fast and accurately, even before relying the information to higher brain areas or more complex system components downstream. Today, advanced convolutional artificial neural networks can successfully solve visual detection and classification tasks and are commonly used to build complex decision making systems. However, in order to perform well on these tasks they require increasingly complex, "very deep" model structure, which is costly in inference run-time, energy consumption and number of training samples, only trainable on cloud-computing clusters. A single spiking neuron has been shown to be able to solve recognition tasks for homogeneous Poisson input statistics, a commonly used model for spiking activity in the neocortex. When modeled as leaky integrate and fire with gradient decent learning algorithm it was shown to posses a variety of complex computational capabilities. Here we improve its implementation. We also account for more natural stimulus generated inputs that deviate from this homogeneous Poisson spiking. The improved gradient-based local learning rule allows for significantly better and stable generalization. We also show that with its improved capabilities it can count weakly labeled concepts by applying our model to a problem of multiple instance learning (MIL) with counting where labels are only available for collections of concepts. In this counting MNIST task the neuron exploits the improved implementation and outperforms conventional ConvNet architecture under similar condtions.

arXiv:1806.02374

Fast Context-Annotated Classification of Different Types of Web Service Descriptions

In the recent rapid growth of web services, IoT, and cloud computing, many web services and APIs appeared on the web. With the failure of global UDDI registries, different service repositories started to appear, trying to list and categorize various types of web services for client applications' discover and use. In order to increase the effectiveness and speed up the task of finding compatible Web Services in the brokerage when performing service composition or suggesting Web Services to the requests, high-level functionality of the service needs to be determined. Due to the lack of structured support for specifying such functionality, classification of services into a set of abstract categories is necessary. We employ a wide range of Machine Learning and Signal Processing algorithms and techniques in order to find the highest precision achievable in the scope of this article for the fast classification of three type of service descriptions: WSDL, REST, and WADL. In addition, we complement our approach by showing the importance and effect of contextual information on the classification of the service descriptions and show that it improves the accuracy in 5 different categories of services.

arXiv:2607.22806v1cs.LG

지리 분산 서버리스 클라우드에서 SLA 제약 탄소 인식 라우팅

SLA-Constrained Carbon-Aware Routing in Geo-Distributed Serverless Clouds

현대 클라우드 배포는 애플리케이션을 여러 지리적 리전에 분산하지만, 표준 라우팅 메커니즘은 지연 시간(latency)을 우선시하면서 지역 전력망의 변동하는 탄소 집약도(carbon intensity)를 무시한다. 지연 시간 중심 라우팅은 특히 더 깨끗한 리전이 허용 가능한 지연 시간 범위 내에 있을 때 불필요한 탄소 배출을 초래한다. 제안된 모델은 탄소 인식 서버리스 라우팅 문제를 지리 분산 클라우드 리전에 대한 제약 최적화(constrained optimization)로 공식화하고, SLA-실행 가능 영역 내에서 최적의 탄소 감축을 달성하는 SLA 제약 탄소 인식 라우팅 정책을 도입하며, 이를 5개 주요 AWS 배포에 걸친 실제 탄소 집약도 측정값으로 평가한다. 실험 결과, 제안된 정책은 평가된 모든 임계값에서 SLA 위반 없이 최대 46.8%의 탄소 감축을 달성한다. 해당 시스템은 혼합 워크로드(mixed workloads) 하에서 평균 27.4%의 탄소를 감축하며, 라우팅 오버헤드는 매우 낮다(총 요청 지연 시간의 0.02% 미만). 6개 대륙에 걸친 12개 AWS 리전에 대한 확장성(scalability) 연구는 혼합 워크로드 하에서 라우팅 유연성이 확대됨에 따라 평균 탄소 절감이 27.4%에서 47.5%로 증가함을 보여준다. 제안된 연구는 저탄소 라우팅 결정을 가능하게 함으로써 SDG 13(기후 행동) 및 SDG 7(경제적이고 깨끗한 에너지)에 기여한다. 이 결과는 클라우드 시스템이 사용자 경험을 저해하지 않으면서도 상당한 탄소 절감을 달성할 수 있음을 시사한다.

arXiv:2607.13035v1cs.CL

FixItFlow: 클라우드 인시던트로부터의 자동 트러블슈팅 가이드 생성

FixItFlow: Automated Troubleshooting Guide Generation from Cloud Incidents

클라우드 서비스는 신속한 진단과 해결이 필요한 잦은 인시던트를 겪는다. 트러블슈팅 가이드는 엔지니어가 일관되게 대응하도록 돕지만, 수동으로 작성하는 것은 노동 집약적이어서 커버리지가 불완전하고 문서가 구식이 되는 결과를 낳는다. 우리는 대규모 언어 모델(LLM)을 사용해 과거 인시던트 데이터로부터 트러블슈팅 가이드를 생성하는 자동화 시스템 FixItFlow를 제안한다. 이 시스템은 엔지니어의 조치에서 진단 패턴을 추출하고, 검증된 명령어가 포함된 구조화된 가이드를 합성하며, 허구의 내용을 방지하기 위해 엄격한 검증을 적용한다. 26명의 엔지니어를 대상으로 한 평가에서, 생성된 가이드는 명확성에 대해 61.5%의 긍정 평가를 받았으며, 관련 가이드가 있는 인시던트에 대해 완화 시간을 2.3배 줄였다. 이 결과는 자동화된 가이드 생성이 엔지니어 팀의 문서화 부담을 줄이면서 인시던트 대응을 개선할 수 있음을 보여준다.