检索结果-内蒙古大学图书馆

Detecting and Mitigating Collusive Interest Flooding Attacks in Named Data Networking

IEEE ACCESS 2022年 10卷 65996-66017页

作者： Al-Share, Rama A. Shatnawi, Ahmed S. Al-Duwairi, Basheer Jordan Univ Sci & Technol Dept Network Engn & Secur Irbid 22110 Jordan Jordan Univ Sci & Technol Dept Software Engn Irbid 22110 Jordan

The large expansion in network services and applications seen in the last few years requires new network architectures to satisfy an increasing number of users and enhance content delivery. Named Data Networking (NDN) has recently appeared as a new paradigm to solve many shortcomings in the current TCP/IP architecture. Its main characteristics like stateful forwarding and in-network caching made NDN networks an efficient environment for data delivery where the data is retrieved based on content names rather than IP addresses. The NDN, by its nature, defends against the well-known Distributed Denial of Service (DDoS) attacks that take place in the traditional TCP/IP architecture. However, a special kind of DDoS attack called Collusive Interest Flooding Attack (CIFA) has appeared to overwhelm the resources of NDN routers by filling their Pending Interest Tables (PIT) with long-lasting malicious entries. The network throughput and consumer satisfaction rate are highly affected by CIFA. A lightweight yet efficient stateless CIFA detection algorithm is proposed in this research utilizing the non-parametric CUSUM algorithm;a change point detection approach that detects the point in time when a transition occurs in the network. The proposed algorithm is characterized by its low computational overhead, highly accurate detection, and quick response. To detect the malicious name prefixes and eliminate the CIFA effect, a mitigation algorithm that uses the average response time vales of all name prefixes is proposed in this research. Experimental results show that this approach detects CIFA after 199.5 ms from when an attack is launched in the large-scale topology. In addition, the mitigation approach effectively reduces the PIT utilization and increases the average consumer satisfaction rate.

关键词： Computer architecture Security Floods TCPIP Internet Throughput detection algorithms Collusive interest flooding attack (CIFA) denial of service detection and mitigation scheme named data networking (NDN) non-parametric cumulative sum (CUSUM)

来源：评论

学校读者我要写书评

暂无评论

Multi-Regime Analysis for Computer Vision- Based Traffic Surveillance Using a Change-Point detection Algorithm

引用

IEEE ACCESS 2021年 9卷 40980-40995页

作者： Jeong, Seungyun Roh, Seungbin Sohn, Keemin Chung Ang Univ Dept Urban Engn Seoul 06974 South Korea

As a result of significant advances in deep learning, computer vision technology has been widely adopted in the field of traffic surveillance. Nonetheless, it is difficult to find a universal model that can measure traffic parameters irrespective of ambient conditions such as times of the day, weather, or shadows. These conditions vary recurrently, but the exact points of change are inconsistent and unpredictable. Thus, the application of a multi-regime method would be problematic, even when separate sets of model parameters are prepared in advance. In the present study we devised a robust approach that facilitates multi-regime analysis. This approach employs an online parametric algorithm to determine the change-points for ambient conditions. An autoencoder was used to reduce the dimensions of input images, and reduced feature vectors were used to implement the online change-point algorithm. Seven separate periods were tagged with typical times in a given day. Multi-regime analysis was then performed so that the traffic density could be separately measured for each period. To train and test models for vehicle counting, 1,100 video images were randomly chosen for each period and labeled with traffic counts. The measurement accuracy of multi-regime analysis was much higher than that of an integrated model trained on all data.

关键词： Feature extraction Traffic control Surveillance Density measurement Training Detectors detection algorithms Change-point algorithm autoencoder traffic surveillance multi-regime model traffic density

来源：评论

学校读者我要写书评

暂无评论

eXplainable and Reliable Against Adversarial Machine Learning in Data Analytics

引用

IEEE ACCESS 2022年 10卷 83949-83970页

作者： Vaccari, Ivan Carlevaro, Alberto Narteni, Sara Cambiaso, Enrico Mongelli, Maurizio Consiglio Nazl Ric CNR IEIIT Inst I-16149 Genoa Italy Univ Genoa Dept Elect Elect & Telecommun Engn & Naval Archit I-16145 Genoa Italy Politecn Torino Dept Control & Comp Engn DAUIN I-10129 Turin Italy

Machine learning (ML) algorithms are nowadays widely adopted in different contexts to perform autonomous decisions and predictions. Due to the high volume of data shared in the recent years, ML algorithms are more accurate and reliable since training and testing phases are more precise. An important concept to analyze when defining ML algorithms concerns adversarial machine learning attacks. These attacks aim to create manipulated datasets to mislead ML algorithm decisions. In this work, we propose new approaches able to detect and mitigate malicious adversarial machine learning attacks against a ML system. In particular, we investigate the Carlini-Wagner (CW), the fast gradient sign method (FGSM) and the Jacobian based saliency map (JSMA) attacks. The aim of this work is to exploit detection algorithms as countermeasures to these attacks. Initially, we performed some tests by using canonical ML algorithms with a hyperparameters optimization to improve metrics. Then, we adopt original reliable AI algorithms, either based on eXplainable AI (Logic Learning Machine) or Support Vector Data Description (SVDD). The obtained results show how the classical algorithms may fail to identify an adversarial attack, while the reliable AI methodologies are more prone to correctly detect a possible adversarial machine learning attack. The evaluation of the proposed methodology was carried out in terms of good balance between FPR and FNR on real world application datasets: Domain Name System (DNS) tunneling, Vehicle Platooning and Remaining Useful Life (RUL). In addition, a statistical analysis was performed to improve the robustness of the trained models, including evaluating their performance in terms of runtime and memory consumption.

关键词： Machine learning algorithms Reliability Adversarial machine learning Prediction algorithms Machine learning Data models Safety Object detection Machine learning detection algorithms adversarial machine learning reliable

来源：评论

学校读者我要写书评

暂无评论

A Robust Algorithm Based on Link Label Propagation for Identifying Functional Modules From Protein-Protein Interaction Networks

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022年第3期19卷 1435-1448页

作者： Jiang, Hao Zhan, Fei Wang, Congtao Qiu, Jianfeng Su, Yansen Zheng, Chunhou Zhang, Xingyi Zeng, Xiangxiang Anhui Univ Sch Comp Sci & Technol Minist Educ Key Lab Intelligent Comp & Signal Proc Hefei 230601 Peoples R China Hunan Univ Sch Informat Sci & Engn Changsha 410082 Peoples R China

Identifying functional modules in protein-protein interaction (PPI) networks elucidates cellular organization and mechanism. Various methods have been proposed to identify the functional modules in PPI networks, but most of these methods do not consider the noisy links in PPI networks. They achieve a competitive performance on the PPI networks without noisy links, but the performance of these methods considerably deteriorates in the noisy PPI networks. Furthermore, the noisy links are inevitable in the PPI networks. In this paper, we propose a novel link-driven label propagation algorithm (LLPA) to identify functional modules in PPI networks. The LLPA first find link clusters in PPI networks, and then the functional modules are identified from the link clusters. Two strategies aimed to ensure the robustness of LLPA are proposed. One strategy involves the proposed LLPA updating the link labels in accordance with the designed weight of the link, which can reduce the incidence of noisy links. The other strategy involves the filtration of some noisy labels from the link clusters to further reduce the influence of noisy links. The performance evaluation on three real PPI networks shows that LLPA outperforms other eight state-of-the-art detection algorithms in terms of accuracy and robustness.

关键词： Noise measurement Proteins Robustness Clustering algorithms detection algorithms Signal processing algorithms Partitioning algorithms Functional modules identification link label propagation nosiy link protein-protein interaction network

来源：评论

学校读者我要写书评

暂无评论

Patch-Antenna-Based Structural Strain Measurement Using Optimized Energy detection Algorithm Applied on USRP

引用

IEEE INTERNET OF THINGS JOURNAL 2021年第9期8卷 7476-7484页

作者： Wan, Guo Chun Li, Meng Meng Yang, Yu Lu Xie, Liyu Chen, Lan Tongji Univ Sch Microelect Sci & Engn Shanghai 200092 Peoples R China Tongji Univ Coll Civil Engn Shanghai 200092 Peoples R China Shanghai Inst Technol Sch Elect & Elect Engn Shanghai 201418 Peoples R China

A new structural health monitoring (SHM) program using spectrum sensing and radio-frequency identification technology is presented to measure structural strain. The proposed program involving universal software radio peripheral (USRP) provides an economical alternative to these type of measurements as compared to high-end equipment while this method can achieve more flexible data processing. The overall system for strain detection consists of three main parts: 1) a patch antenna as the sensor for strain;2) an USRP as a measuring instrument;3) a computer for data processing. The patch antenna can be used to measure structural strain by interrogating resonant frequency shift due to changes in antenna length. In this article we use the optimized energy detection algorithm applied on USRP to detect the spectrum of the patch antenna, the final measurement results show that the patch antenna sensor has a strain sensitivity 1.7678 kHz/mu e while the error between the measured value and the true value of the stress is 2.443% after corrected by machine learning.

关键词： Antenna measurements Patch antennas Measurement uncertainty Energy measurement Strain measurement Broadband antennas detection algorithms Energy detection machine learning strain measurement universal software radio peripheral (USRP)

来源：评论

学校读者我要写书评

暂无评论

Sparsity Signal detection for Indoor GSSK-VLC System

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2021年第12期70卷 12975-12984页

作者： Zuo, Ting Wang, Fasong Zhang, Jiankang Zhengzhou Univ Sch Informat Engn Zhengzhou 450001 Henan Peoples R China Bournemouth Univ Dept Comp & Informat Bournemouth BH12 5BB Dorset England

In this article, the signal detection problem in indoor visible light communication (VLC) system aided by generalized space shift keying (GSSK) is modeled as a sparse signal reconstruction problem, which has lower computational complexity by exploiting the sparse reconstruction algorithms in compressed sensing (CS). In order to satisfy the measurement matrix property to perform sparse signal reconstruction, a preprocessing approach of measurement matrix is proposed based on singular value decomposition (SVD), which theoretically guarantees the feasibility of utilizing CS based sparse signal detection method in indoor GSSK-VLC system. Then, by adopting classical orthogonal matching pursuit (OMP) algorithm and compressed sampling matching pursuit (CoSaMP) algorithm, the GSSK signals are efficiently detected in the considered indoor GSSK-VLC system. Furthermore, a more efficient detection algorithm combined with OMP and maximum likelihood (ML) is also presented especially for SSK scenario. Finally, the effectiveness of the proposed sparsity aided detection algorithms in indoor GSSK-VLC system are verified by computer simulations. The results show that the proposed algorithms can achieve better bit error rate (BER) and lower computation complexity than ML based detection method. Specifically, a signal-to-noise ratio (SNR) gain as high as 12 dB is observed in the SSK scenario and about 5 dB in case of a GSSK scenario upon employing our proposed detection methods.

关键词： Matching pursuit algorithms Visible light communication Signal detection Radio frequency Lighting detection algorithms Sparse matrices Visible light communication (VLC) generalized space shift keying (GSSK) compressed sensing (CS) maximum likelihood (ML) signal detection

来源：评论

学校读者我要写书评

暂无评论

Phase Loss detection Using Current Signals: A Review

引用

IEEE ACCESS 2021年 9卷 114727-114740页

作者： Dianov, Anton Anuchin, Alecksey Moscow Power Engn Inst Dept Elect Drives Moscow 111250 Russia

This paper discusses open phase faults, which can happen in a system grid-converter-motor drive, and measures to properly handle this type of fault. The authors of this paper provide classification of algorithms used for the detection of the loss of phase and explain the distinctive features of each group of methods. They review existing algorithms, which are based on the analysis of the current signals, discuss their pros and cons and suggest possible areas of usage for each group of methods. The authors also propose one novel method for detection of open phase, which was developed for low-cost systems with low resolution analog-to digital converters (ADC). This paper mainly considers methods for three-phase motors as the most popular machines, however some algorithms can be used in multiphase drives. The authors of the paper also share their more than 20 years' experience combined, in this area, which was obtained by developing industrial and commercial drives, and focus on the requirements of the IEC/UL 60730 safety standard, where the phase-loss detection algorithm is one of the essential parts of control system.

关键词： Sensors Induction motors Voltage control Current measurement Standards Sensor systems detection algorithms Motor drives fault diagnosis fault protection fault tolerant control

来源：评论

学校读者我要写书评

暂无评论

A List detection Algorithm for Full Diversity Codebooks Based on the Combinatorial Approach

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2021年第4期10卷 805-809页

作者： Inacio, Juliana C. Uchoa-Filho, Bartolomeu F. Le Ruyet, Didier Univ Fed Santa Catarina Dept Elect Engn BR-88040900 Florianopolis SC Brazil Conservatoire Natl Arts & Metiers CEDRIC LAETITIA F-75003 Paris France

A combinatorial approach was recently proposed for designing multidimensional codebooks for fading channels. Albeit flexible and granting full signal space diversity, it relies on the optimal maximum likelihood detection, which is rather complex. In this letter, we propose an alternative low-complexity, list-based detection algorithm for the codebooks under this approach. The detection complexity of the proposed algorithm is analyzed, and simulation results for both detection complexity and error performance are presented. It is concluded that the proposed detection algorithm not only preserves the diversity gain but also presents an excellent performance-complexity trade-off, thus adding value to the combinatorial approach.

关键词： Complexity theory Diversity methods detection algorithms Maximum likelihood decoding Upper bound Signal to noise ratio Random variables Full diversity list decoding signal-space diversity

来源：评论

学校读者我要写书评

暂无评论

Decaying DC and Harmonic Components detection for Absorbing Impact Load Currents in Weak Grids

引用

IEEE TRANSACTIONS ON POWER DELIVERY 2021年第3期36卷 1907-1910页

作者： Xiong, Liansong Liu, Xiaokang Liu, Yonghui Nanjing Inst Technol Sch Automat Nanjing 211167 Peoples R China Xi An Jiao Tong Univ Sch Elect Engn Xian 710049 Peoples R China Politecn Milan Dept Elect Informat & Bioengn I-20133 Milan Italy

Decaying DC (DDC) current due to impact loads causes detrimental consequences in weak grids. In this paper, the active power filter (APF) is enhanced to simultaneously compensate for the undesired harmonics, negative sequence components and the DDC component in the event of a transient. To this end, first, a novel DDC component detection method is mathematically deduced for single-phase transient current, followed by its extension to the three-phase system. With respect to existing techniques, the proposed method has a significantly reduced detection time from 1 grid cycle to approximately 0.5 grid cycle. By further exploiting the transient signal properties in dq-frame, the three-phase fundamental-frequency current in positive sequence can be separated. Finally, the enhanced APF control scheme is developed based on the proposed detection algorithm. Experiments verified the effectiveness and advancement of the proposed technique.

关键词： Transient analysis Harmonic analysis Power system harmonics Time-frequency analysis Steady-state detection algorithms Time factors Active power filter decaying DC component harmonic elimination power quality transient impact currents

来源：评论

学校读者我要写书评

暂无评论

A Novel Sum-Product detection Algorithm for Faster-Than-Nyquist Signaling: A Deep Learning Approach

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2021年第9期69卷 5975-5987页

作者： Liu, Bryan Li, Shuangyang Xie, Yixuan Yuan, Jinhong Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2033 Australia

A deep learning assisted sum-product detection algorithm (DL-SPDA) for faster-than-Nyquist (FTN) signaling is proposed in this paper. The proposed detection algorithm works on a modified factor graph which concatenates a neural network function node to the variable nodes of the conventional FTN factor graph to approach the maximum a posterior probabilities (MAP) error performance. In specific, the neural network performs as a function node in the modified factor graph to deal with the residual intersymbol interference (ISI) that is not considered by the conventional detector with a limited complexity. We modify the updating rule in the conventional sum-product algorithm so that the neural network assisted detector can be complemented to a turbo equalization receiver. Furthermore, we propose a compatible training technique to improve the detection performance of the proposed DL-SPDA with turbo equalization. In particular, the neural network is optimized in terms of the mutual information between the transmitted sequence and the extrinsic information. We also investigate the maximum-likelihood bit error rate (BER) performance of a finite length coded FTN system. Simulation results show that the error performance of the proposed algorithm approaches the MAP performance, which is consistent with the analytical BER.

关键词： Artificial neural networks Detectors Training detection algorithms Complexity theory Receivers Signal processing algorithms Faster-than-Nyquist signaling signal detection deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：