Browsing by Author "Huang, Chun-Ying"

Now showing 1 - 20 of 21

A fuzzy pattern-based filtering algorithm for botnet detection
(2011-10-27)
Wang, Kuochen
;
Huang, Chun-Ying
;
Lin, Shang-Jyh
;
Lin, Ying-Dar
;
資訊工程學系
Botnet has become a popular technique for deploying Internet crimes. Although signature-based bot detection techniques are accurate, they could be useless when bot variants are encountered. Therefore, behavior-based detection techniques become attractive due to their ability to detect bot variants and even unknown bots. In this paper, we propose a behavior-based botnet detection system based on fuzzy pattern recognition techniques. We intend to identify hot-relevant domain names and IP addresses by inspecting network traces. If domain names and IP addresses used by botnets can be identified, the information can be further used to prevent protected hosts from becoming one member of a botnet. To work with fuzzy pattern recognition techniques, we design several membership functions based on frequently observed bots' behavior including: (1) generate failed DNS queries; (2) have similar DNS query intervals; (3) generate failed network connections; and (4) have similar payload sizes for network connections. Membership functions can be easily altered, removed, or added to enhance the capability of the proposed system. In addition, to improve the overall system performance, we develop a traffic reduction algorithm to reduce the amount of network traffic required to be inspected by the proposed system. Performance evaluation results based on real traces show that the proposed system can reduce more than 70% input raw packet traces and achieve a high detection rate (about 95%) and a low false positive rates (0-3.08%). Furthermore, the proposed FPRF algorithm is resource-efficient and can identify inactive botnets to indicate potential vulnerable hosts. (C) 2011 Elsevier B.V. All rights reserved.
Behavior-based botnet detection in parallel
(2014-11-01)
Wang, Kuochen
;
Huang, Chun-Ying
;
Tsai, Li-Yang
;
Lin, Ying-Dar
;
資訊工程學系
Botnet has become one major Internet security issue in recent years. Although signature-based solutions are accurate, it is not possible to detect bot variants in real-time. In this paper, we propose behavior-based botnet detection in parallel (BBDP). BBDP adopts a fuzzy pattern recognition approach to detect bots. It detects a bot based on anomaly behavior in domain name service (DNS) queries and transmission control protocol (TCP) requests. With the design objectives of being efficient and accurate, a bot is detected using the proposed five-stage process, including: (i) traffic reduction, which shrinks an input trace by deleting unnecessary packets; (ii) feature extraction, which extracts features from a shrunk trace; (iii) data partitioning, which divides features into smaller pieces; (iv) DNS detection phase, which detects bots based on DNS features; and (v) TCP detection phase, which detects bots based on TCP features. The detection phases, which consume approximately 90% of the total detection time, can be dispatched to multiple servers in parallel and make detection in real-time. The large scale experiments with the Windows Azure cloud service show that BBDP achieves a high true positive rate (95%+) and a low false positive rate (approximate to 3%). Meanwhile, experiments also show that the performance of BBDP can scale up linearly with the number of servers used to detect bots. Copyright (c) 2013 John Wiley & Sons, Ltd.
Best Papers of the ACM Multimedia Systems (MMSys) Conference 2017 and the ACM Workshop on Network and Operating System Support for Digital Audio and Video (NOSSDAV) 2017
(2018-08-01)
Cesar, Pablo
;
Hsu, Cheng-Hsin
;
Huang, Chun-Ying
;
Hui, Pan
;
交大名義發表
Capacity pricing mechanism for wafer fabrication
(2008-10-01)
Chung, Shu-Hsing
;
Lee, Amy H. I.
;
Huang, Chun-Ying
;
Chuang, Chia-Chien
;
工業工程與管理學系
Wafer fabrication is perhaps the most capital-intensive and technology-intensive industry. Due to customer demand uncertainty, the wafer fabrication industry in Taiwan became dramatically competitive. Emergency orders demanded from customers may exist for the need of time-to-market. How to respond to emergency orders from customers, to analyze the impact to production and cost, and to design an appropriate order acceptance plan, have become an important task for enterprises in pursuing higher service quality and ultimate profit maximization. In this paper, we propose a capacity pricing mechanism to evaluate the impacts of emergency orders. The mechanism is constructed under the circumstances that master production scheduling (MPS), capacity requirement planning (CRP), and data for manufacturing costs are known. Through production planning and profit analysis, the mechanism can analyze pricing factors including the process plans of products, priority levels of products, urgency of orders, and number of layers of poly and metal, so as to reflect the length of cycle time, waiting-time savings, impact to cycle time variance of all orders, and usage amount of critical resources. The capacity price for each product type under each priority level can be determined as a result. (C) 2008 Elsevier Ltd. All rights reserved.
Decapitation via Digital Epidemics: A Bio-Inspired Transmissive Attack
(2016-06)
Chen, Pin-Yu
;
Lin, Ching-Chao
;
Cheng, Shin-Ming
;
Hsiao, Hsu-Chun
;
Huang, Chun-Ying
The evolution of communication technology and the proliferation of electronic devices have rendered adversaries powerful means for targeted attacks via all sorts of accessible resources. In particular, due to the intrinsic interdependence and ubiquitous connectivity of modern communication systems, adversaries can devise malware that propagates through intermediate hosts to approach the target, to which we refer as transmissive attacks. Inspired by biology, the transmission pattern of such an attack in the digital space much resembles the spread of an epidemic in real life. This article describes transmissive attacks, summarizes the utility of epidemic models in communication systems, and draws connections between transmissive attacks and epidemic models. Simulations, experiments, and ongoing research challenges on transmissive attacks are also addressed.
Design and Implement Binary Fuzzing based on libFuzzer
(2018-01-01)
Chao, Wei-Chieh
;
Lin, Si-Chen
;
Chen, Yi-Hsien
;
Tien, Chin-Wei
;
Huang, Chun-Ying
We design and implement libFuzzer-bin, a coverage-guided binary fuzzer based on libFuzzer. We discuss how libFuzzer-bin is implemented, measure the overheads of our implementation, and compare its performance against the American Fuzzy Lop (AFL) fuzzer. This is a work-in-progress. Our evaluation results show that, compared with the vanilla AFL, the current implementation brings only limited overheads and is able to identify possible vulnerabilities in a shorter time.
Energy-Efficient Gas Recognition System with Event-Driven Power Control
(2015)
Huang, Chun-Ying
;
Huang, Po-Tsang
;
Yang, Chih-Chao
;
Chuang, Ching-Te
;
Hwang, Wei
For energy-limited applications of electronic nose, an application-specific architecture is essential to realize a low-energy gas recognition system. In this paper, a pseudo-zeroleakage gas recognition system is proposed to recognize different gases using event-driven power control. Additionally, this gas recognition system can recognize four different gases with concentration information by drift-insensitive on-line training, achieving 100% recognition accuracy for gas type and 89.4% accuracy for concentration analysis. For further reducing the overall energy consumption, both near-threshold SRAM and low-voltage embedded ReRAM are integrated into the proposed system, respectively. Based on TSMC 65nm LP CMOS process, the total energy of the gas recognition systems with SRAM and ReRAM are only 8.62 mu J and 2.04 mu J in a sensing period, respectively. Hence, an energy-efficient gas recognition system can be realized by a pseudo-zero-leakage event-driven structure with ReRAM.
Enhanced external quantum efficiency in GaN-based vertical-type light-emitting diodes by localized surface plasmons
(2016-03-03)
Yao, Yung-Chi
;
Hwang, Jung-Min
;
Yang, Zu-Po
;
Haung, Jing-Yu
;
Lin, Chia-Ching
Enhancement of the external quantum efficiency of a GaN-based vertical-type light emitting diode (VLED) through the coupling of localized surface plasmon (LSP) resonance with the wave-guided mode light is studied. To achieve this experimentally, Ag nanoparticles (NPs), as the LSP resonant source, are drop-casted on the most top layer of waveguide channel, which is composed of hydrothermally synthesized ZnO nanorods capped on the top of GaN-based VLED. Enhanced light-output power and external quantum efficiency are observed, and the amount of enhancement remains steady with the increase of the injected currents. To understand the observations theoretically, the absorption spectra and the electric field distributions of the VLED with and without Ag NPs decorated on ZnO NRs are determined using the finite-difference time-domain (FDTD) method. The results prove that the observation of enhancement of the external quantum efficiency can be attributed to the creation of an extra escape channel for trapped light due to the coupling of the LSP with wave-guided mode light, by which the energy of wave-guided mode light can be transferred to the efficient light scattering center of the LSP.
Hardware Design for Statistical Network Traffic Classifiers
(2016-01-01)
Lu, Chun-Nan
;
Lai, Yuan-Cheng
;
Huang, Chun-Ying
;
Lin, Ying-Dar
;
資訊工程學系
Signature matching is commonly used in network traffic classification and can provide accurate and efficient results. However, it requires constant updates of signatures and can't be applied to encrypted traffic. Statistical behavior-based approaches can avoid the drawback of payload encryption. However, the computational complexity of related statistical features may prevent them being deployed in systems that are expected to respond in limited time. In this work, we combine the advantages of statistics-based classification approaches and hardware design techniques to develop a balanced classifier that can provide timely responses to. Two statistics-based solutions, a message size distribution classifier (MSDC) and a message size sequence classifier (MSSC) which depend on classification accuracy and real timeliness arc proposed. The former aims to identify network flows in an accurate but not-so-fast manner, while the latter aims to provide a lightweight and real-time solution. Simulations showed that MSSC contributed 77.4% and MSDC contributed 22.6% of decision rounds. Furthermore, our design can achieve an accuracy of more than 94% while achieving a throughput of 80 Gbps.
Heuristic algorithms to solve the capacity allocation problem in photolithography area (CAPPA)
(2008-06-01)
Chung, Shu-Hsing
;
Huang, Chun-Ying
;
Lee, Amy H. I.
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
Wafer fabrication is one of the most complex and high competence manufacturing. How to fully utilize the machine capacity to meet customer demand is a very important topic. In this paper, we address the capacity allocation problem for photolithography area (CAPPA), which belongs to a capacity requirement planning scheme, with the process window and machine dedication restrictions that arise from an advanced wafer fabrication technology environment. Process window means that a wafer needs to be processed on machines that can satisfy its process capability (process specification). Machine dedication means that once the first critical layer of a wafer lot is processed on a certain machine, the subsequent critical layers of this lot must be processed on the same machine to ensure good quality of final products. We present six modified heuristics and a linear-programming-based heuristic algorithm (LPBHA) to solve the problem efficiently. The performance of the proposed algorithms is tested using real-world CAPPA cases taken from wafer fabrication photolithography area. Computational results show that LPBHA is the most effective one, and with a least average and a least standard deviation of deviation ratio of 0.294 and 0.085% compared to the lower bound of the CAPPA.
High performance traffic classification based on message size sequence and distribution
(2016-12)
Lu, Chun-Nan
;
Huang, Chun-Ying
;
Lin, Ying-Dar
;
Lai, Yuan-Cheng
;
資訊工程學系
Classifying network flows into applications is a fundamental requirement for network administrators. Administrators used to classify network applications by examining transport layer port numbers or application level signatures. However, emerging network applications often send encrypted traffic with randomized port numbers. This makes it challenging to detect and manage network applications. In this paper, we propose two statistics-based solutions, the message size distribution classifier (MSDC) and the message size sequence classifier (MSSC) depending on classification accuracy and real timeliness. The former aims to identify network flows in an accurate manner, while the latter aims to provide a lightweight and real-time solution. The proposed classifiers can be further combined to build a hybrid solution that achieves both good detection accuracy and short response latency. Our numerical results show that the MSDC can make a decision by inspecting less than 300 packets and achieve a high detection accuracy of 99.98%. In contrast, the MSSC classifier can respond by only looking at the very first 15 packets and have a slightly lower accuracy of 94.99%. Our implementations on a commodity personal computer show that running the MSDC, the MSSC, and the hybrid classifier in-line achieves a throughput of 400 Mbps, 800 Mbps, and 723 Mbps, respectively.
Is Foveated Rendering Perceivable in Virtual Reality? Exploring the Efficiency and Consistency of Quality Assessment Methods
(2017-01-01)
Hsu, Chih-Fan
;
Chen, Anthony
;
Hsu, Cheng-Hsin
;
Huang, Chun-Ying
;
Lei, Chin-Laung
Foveated rendering leverages human visual system to increase video quality under limited computing resources for Virtual Reality (VR). More specifically, it increases the frame rate and the video quality of the foveal vision via lowering the resolution of the peripheral vision. Optimizing foveated rendering systems is, however, not an easy task, because there are numerous parameters that need to be carefully chosen, such as the number of layers, the eccentricity degrees, and the resolution of the peripheral region. Furthermore, there is no standard and efficient way to evaluate the Quality of Experiment (QoE) of foveated rendering systems. In this paper, we propose a framework to compare the performance of different subjective assessment methods on foveated rendering systems. We consider two performance metrics: efficiency and consistency, using the perceptual ratio, which is the probability of the foveated rendering is perceivable by users. A regression model is proposed to model the relationship between the human perceived quality and foveated rendering parameters. Our comprehensive study and analysis reveal several insights: 1) there is no absolute superior subjective assessment method, 2) subjects need to make more observations to confirm the foveated rendering is imperceptible than perceptible, 3) subjects barely notice the foveated rendering with an eccentricity degree of 7.5 degrees + and peripheral region of a resolution of 540p+, and 4) QoE levels are highly dependent on the individuals and scenes. Our findings are crucial for optimizing the foveated rendering systems for future VR applications.
Low Power Algorithm-Architecture Co-Design of Fast Independent Component Analysis (FICA) for Multi-Gas Sensor Applications
(2015)
Yang, Chieh-Chao
;
Huang, Po-Tsang
;
Huang, Chun-Ying
;
Chuang, Ching-Te
;
Hwang, Wei
For miniaturized multi-gas sensors, the detected multi-gas signals would be self-interfered by responses to multiple gases. In this paper, a fast Independent Component Analysis ( FICA) is proposed to restore the original source signals from the mixed signals received by different gas sensors. This FICA is designed and implemented by low power algorithm-architecture co-design considering the trade-offs among power, delay and accuracy of extracted signals for multigas sensor applications. To further reduce the power consumption, a data-length controller is designed to adjust the calculated data-length. Additionally, a stability check unit is utilized to terminate the ICA execution for reduction of the computation time and total energy. Compared with the conventional ICA design, the proposed low-power FICA realizes energy reduction by 75% for multi-gas sensor applications.
Mobile Application Security
(2014-06-01)
Lin, Ying-Dar
;
Huang, Chun-Ying
;
Wright, Matthew
;
Kambourakis, Georgios
;
交大名義發表
With a multitude of mobile apps available in the market, most users are unaware of the security risks they bring. Strategies for coping with the diversity of these threats deserve a closer look.
Optimizing Fixation Prediction Using Recurrent Neural Networks for 360 degrees Video Streaming in Head-Mounted Virtual Reality
(2020-03-01)
Fan, Ching-Ling
;
Yen, Shou-Cheng
;
Huang, Chun-Ying
;
Hsu, Cheng-Hsin
;
資訊工程學系
We study the problem of predicting the viewing probability of different parts of 360. videos when streaming them to head-mounted displays. We propose a fixation prediction network based on recurrent neural network, which leverages sensor and content features. The content features are derived by computer vision (CV) algorithms, which may suffer from inferior performance due to various types of distortion caused by diverse 360. video projection models. We propose a unified approach with overlapping virtual viewports to eliminate such negative effects, andwe evaluate our proposed solution using severalCValgorithms, such as saliency detection, face detection, and object detection. We find that overlapping virtual viewports increase the performance of these existing CV algorithms that were not trained for 360. videos. We next fine-tune our fixation prediction network with diverse design options, including: 1) with or without overlapping virtual viewports, 2) with or without future content features, and 3) different feature sampling rates. We empirically choose the best fixation prediction network and use it in a 360. video streaming system. We conduct extensive trace-driven simulations with a large-scale dataset to quantify the performance of the 360. video streaming system with different fixation prediction algorithms. The results show that our proposed fixation prediction network outperforms other algorithms in several aspects, such as: 1) achieving comparable video quality (average gaps between -0.05 and 0.92 dB), 2) consuming much less bandwidth (average bandwidth reduction by up to 8Mb/s), 3) reducing the rebuffering time (on average 40 s in bandwidth-limited 4G cellular networks), and 4) running in real-time (at most 124 ms).
Scenario-Based Microservice Retrieval Using Word2Vec
(2018-01-01)
Ma, Shang-Pin
;
Chuang, Yen
;
Lan, Ci-Wei
;
Chen, Hsi-Min
;
Huang, Chun-Ying
Microservice architecture (MSA) is an emerging software architectural style, which differs fundamentally from the monolithic, layered architecture. During the development and maintenance of microservice systems, how to provide an effective service retrieval mechanism is a critical challenge to avoid the problems of rework and duplicate code. Meanwhile, nowadays, using the BDD (Behavior-Driven Development) method to develop microservices becomes more and more popular due to its agility and domain-driven characteristics. BDD is an agile software development approach emphasizing that test cases are written in a common language to include scenarios that describe the features of a target system. In this paper, we propose an approach, referred to as SMSR (Scenario based MicroService Retrieval), to recommend appropriate microservices to users based on the user-written BDD test scenarios. The proposed service retrieval algorithm is based on word2vec, a widely-used machine learning method in NLP (Natural Language Processing), to perform service filtering and service similarity calculation. Experiment results show that SMSR is able to effectively retrieve appropriate microservices from the service repository.
Session level flow classification by packet size distribution and session grouping
(2012-01-12)
Lu, Chun-Nan
;
Huang, Chun-Ying
;
Lin, Ying-Dar
;
Lai, Yuan-Cheng
;
資訊工程學系
Classifying traffic into specific network applications is essential for application-aware network management and it becomes more challenging because modern applications complicate their network behaviors. While port number-based classifiers work only for some well-known applications and signature-based classifiers are not applicable to encrypted packet payloads, researchers tend to classify network traffic based on behaviors observed in network applications. In this paper, a session level flow classification (SLFC) approach is proposed to classify network flows as a session, which comprises of flows in the same conversation. SLFC first classifies flows into the corresponding applications by packet size distribution (PSD) and then groups flows as sessions by port locality. With PSD, each flow is transformed into a set of points in a two-dimension space and the distances between each flow and the representatives of pre-selected applications are computed. The flow is recognized as the application having a minimum distance. Meanwhile, port locality is used to group flows as sessions because an application often uses consecutive port numbers within a session. If flows of a session are classified into different applications, an arbitration algorithm is invoked to make the correction. The evaluation shows that SLFC achieves high accuracy rates on both flow and session classifications, say 99.9% and 99.98%, respectively. When SLFC is applied to online classification, it is able to make decisions quickly by checking at most 300 packets for long-lasting flows. Based on our test data, an average of 72% of packets in long-lasting flows can be skipped without reducing the classification accuracy rates. (C) 2011 Elsevier B.V. All rights reserved.
Smart Beholder: An Extensible Smart Lens Platform
(2016)
Huang, Chun-Ying
;
Fan, Ching-Ling
;
Hsu, Chih-Fan
;
Chang, Hsin-Yu
;
Tsai, Tsung-Han
Smart Lenses refer to detachable, orientable and zoomable lenses that stream live videos over wireless networks to heterogeneous computing devices, including tablets and smartphones. Various novel applications are made possible by smart lenses, including mobile photography, smart surveillance cameras, and Unmanned Aerial Vehicle (UAV) cameras. However, to our best knowledge, existing smart lenses are closed and proprietary, and thus we initiate an open-source project called Smart Beholder for end-to-end solutions of smart lenses. The code and documents of Smart Beholder can be found at our website http://www.smartbeholder.org. Our Smart Beholder platform are useful to researchers for fast prototyping, developers for rapid development, and amateurs for hobbies. We have implemented Smart Beholder server (camera) using a popular embedded Linux platform, called Raspberry Pi. We have also realized Smart Beholder client (controller) on various OS\'s, including Android. Our experimental results show the practicality and efficiency of our proposed Smart Beholder: we outperform commercial products in the market in terms of both objective and subjective metrics. We believe the release of Smart Beholder will stimulate future studies on novel multimedia applications enabled by smart lenses.
Stateful traffic replay for web application proxies
(2015-04-01)
Huang, Chun-Ying
;
Lin, Ying-Dar
;
Liao, Peng-Yu
;
Lai, Yuan-Cheng
;
資訊工程學系
It is a common practice to test a network device by replaying network traffic onto it and observe its reactions. Many replay tools support Transmission Control Protocol/Internet Protocol stateful traffic replay and hence can be used to test switches, routers, and gateway devices. However, they often fail if the device under test (DUT) is an application level proxy. In this paper, we design and implement ProxyReplay to replay application-layer traffic for network proxies. As many application proxies have built-in security functions, the main purpose of this tool is to evaluate the security functionalities of DUTs using payloads constructed from real network traces. ProxyReplay modifies requests and responses and maintains queues for request-response pairs to resolve the issues of protocol dependency, functional dependency, concurrent replay, and error resistance. The solution provides two replay modes, that is, the preprocess mode and the concurrent mode. Depending on the benchmark scenario, we show that the preprocess mode is better for benchmarking the performance capability of a DUT. In contrast, the concurrent mode is used when the replayed trace file is extremely large. Our experiments show 99% accuracy. In addition, the replay performance exceeds 320 Mbps by running the benchmark with an off-the-shelf personal computer in the preprocess mode. Copyright (C) 2014 John Wiley & Sons, Ltd.
The Future of Cloud Gaming
(2016-04)
Cai, Wei
;
Shea, Ryan
;
Huang, Chun-Ying
;
Chen, Kuan-Ta
;
Liu, Jiangchuan