检索结果-内蒙古大学图书馆

Automatically derived stateful network functions including non-field attributes

学校读者我要写书评

暂无评论

Automatically derived stateful network functions including n...

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Bin Yuan Shengyao Sun Xianjun Deng Deqing Zou Haoyu Chen Shenghui Li Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Shenzhen Research Institute Huazhong University of Science and Technology Shenzhen China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Cluster and Grid Computing Lab

ISBN: (纸本)9781665416597

The modern network consists of thousands of network devices from different suppliers that perform distinct code-pendent functions, such as routing, switching, modifying header fields, and access control across physical and virtual networks. Because of the network complexity, the network is prone to a wide range of errors, such as false-positive configuration, software errors, or unexpected interactions across protocols. These errors can lead to loops, sub-optimal routing, path leaks, black holes, and access control violations that make services unavailable, vulnerable to exploitation, or prone to attacks (e.g., DDoS attacks). To mitigate these problems, network operators deploy many different stateful network functions, like firewalls, NATs, load balancers, and intrusion-prevention boxes. They have become an important part of networks today, so it is critical to verify that these network functions are the same as expected deployments. All static network verification tools are meant to rigorously check network software or configuration for bugs before deployment. They usually use handwritten models or limited derivation models that are error-prone and ignore the fact that even the same type of network functions (from different vendors) still have different implementation details. In this paper, we propose a tool that can automatically synthesize more realistic and high-fidelity models that include stateful network functions with non-field attributes. We design an inferring algorithm, implement the transformation between data packages and symbolic packages, and obtain a finite state machine that can accurately express the actions of black-box network functions for a given configuration.

关键词： Access control Performance evaluation Privacy Protocols Computational modeling Switches Routing

Discrepancy and Thematic Bibliometric Analyses of the Remaining Limitations in Artificial Intelligence

学校读者我要写书评

暂无评论

Discrepancy and Thematic Bibliometric Analyses of the Remain...

computing (ICOCO), IEEE International Conference on

作者： Mahayaudin M. Mansor Nurain Ibrahim Noor Fadhilah Ahmad Radi Nadirah Abdul Rahim Syarul Heiry Yahaya Mohd Aftar Abu Bakar Roslinazairimah Zakaria School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Malaysia Institute of Big Data Analytics and Artificial Intelligence Universiti Teknologi MARA Malaysia Department of Electrical and Computer Engineering Kuliyyah of Engineering International Islamic University Malaysia Department of Science Computer and Mathematics Universiti Teknologi MARA (Penang Campus) Malaysia Department of Mathematical Sciences Faculty of Science & Technology Universiti Kebangsaan Malaysia Centre for Mathematical Sciences Universiti Malaysia Pahang Al-Sultan Abdullah Malaysia

ISBN: (数字)9798331530303

ISBN: (纸本)9798331530310

As artificial intelligence (AI) advances, it is essential to continuously comprehend its limitations to optimise the integration of AI into autonomous systems that empower humans. The first objective of this study is to highlight the key capabilities of both humans and AI, focusing on the differences and identifying limitations of AI from the literature. Through discrepancy analysis, this study uses a Venn diagram to visualise the remaining limitations of AI into five key domains: (i) emotional intelligence, (ii) consciousness and awareness, (iii) creative imagination, (iv) communication, and (v) ethical decision-making. Furthermore, this study employs thematic bibliometric analysis to provide a more detailed examination of each AI limitation as the second objective. This study has identified underdeveloped and emerging research themes with potential for future development, such as emotion recognition, human-computer interaction, digital health, and situational awareness, which may require further research. Additionally, this study commends the ongoing efforts to harness AI’s computational power and algorithmic innovations to enhance AI’s overall performance and applicability.

关键词： Visualization Technological innovation Ethics Emotion recognition Bibliometrics Decision making Focusing Electronic healthcare Object recognition Artificial intelligence

Galaxy populations of ProtoClusters in cosmological hydrodynamical simulations

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Esposito, Michela Borgani, Stefano Strazzullo, Veronica Pannella, Maurilio Granato, Gian Luigi Ragone-Figueroa, Cinthia Saro, Alex Nonino, Mario Valentini, Milena Department of Physics University of Trieste via G. Tiepolo 11 TriesteI-34131 Italy INAF - Observatory of Trieste via G. Tiepolo 11 TriesteI-34143 Italy IFPU - Institute for Fundamental Physics of The Universe via Beirut 2 TriesteI-34014 Italy INFN - Istituto Nazionale di Fisica Nucleare via Valerio 2 TriesteI-34127 Italy ICSC - Italian Research Center on High Performance Computing Big Data and Quantum Computing via Magnanelli 2 Casalecchio di Reno40033 Italy Universidad Nacional de Córdoba Laprida 854 CórdobaX5000BGR Argentina

Context. The study of protoclusters at cosmic noon is essential for understanding the impact on galaxy properties of the environment and of the transformational processes occurring during this epoch. Aims. This work tests the predictions on galaxy evolution of the DIANOGA cosmological hydrodynamical simulations of cluster progenitors at z = 2.2, comparing them with observations, and investigates the environmental effects on galaxy populations by comparing simulated protoclusters with an average volume of the Universe. Methods. We analyze 14 DIANOGA protoclusters and a cosmological box of 49 cMpc/h per side, simulated with OpenGADGET3. We compare predictions and observations of the galaxy stellar mass function (GSMF), the star-forming Main Sequence (MS), the fraction of star-forming gas, gas depletion times, and the fraction of quenched galaxies. We also compute the rest-frame UV-to-NIR colors of galaxies with the SKIRT-9 radiation transfer code, to analyze UVJ diagrams. Results. We showed that the DIANOGA simulations produce a GSMF in broad agreement with observations. The simulated GSMF shows a higher fraction of high-mass galaxies (M∗ > 1010 M☉) in massive halos in protoclusters, compared to the cosmological box. The same signal, albeit with lower significance, is also observed in the wide-field protocluster structures, indicating an accelerated evolution of galaxies before their infall into massive halos. Our simulations underestimate star formation rates of galaxies both in protoclusters and in the cosmological box, compared to observed counterparts, due to an underestimation of the star-forming gas reservoirs. We find a weak suppression of SFRs in protocluster galaxies (∼ 0.05 dex), compared to the cosmological box, increasing up to ∼ 0.25 dex in massive halos, reflecting suppressed cold gas reservoirs. The quenched galaxy fraction varies significantly across different protocluster halos, consistent with observations at z ∼ 2 − 2.5. The simulations show a stron

关键词： Cosmology

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3DAD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

Tracking Bitcoin-Induced Carbon Trajectory in China Via Refined Spatiotemporal Assessment

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wu, Haochi Wang, Jianxiao Teng, Fei Zhang, Da Cheng, Peng Strbac, Goran Chen, Jiming Sun, Mingyang College ofControlScience andEngineering Zhejiang University Hangzhou310027 China School for EnvironmentandSustainability University ofMichigan Ann ArborMI48109 United States NationalEngineering Laboratory for Big Data Analysis andApplications Peking University Beijing100871 China Peking University Changsha Institute for Computing andDigitalEconomy Changsha410000 China DepartmentofElectricalandElectronic Engineering ImperialCollege London LondonSW72AZ United Kingdom Institute ofEnergy EnvironmentandEconomy Tsinghua University Beijing100084 China MITJointProgram on the Science andPolicy ofGlobalChange CambridgeMA02139 United States

Despite deploying Bitcoin mining machines in renewable energy-rich areas, incompatibility between renewable energy output and Bitcoin mining load, coupled with the interconnected nature of the national power grid operation, have meant that Bitcoin-induced CO2 emissions from China’s heavily coal-based power system have continued to increase and ultimately leads to regulations banning cryptocurrency mining in 2021. Assessing the effects of these regulations requires detailed information on operational and marginal carbon emissions. This study proposes a dynamic regional model for assessing Bitcoin-induced carbon emissions. The cumulative carbon emissions from 2011 to 2021 reached approximately 103 megatonnes. Additionally, the proposed regulatory policy for Bitcoin mining in 2021 is expected to effectively curb carbon emissions by 25.5 megatonnes annually, albeit with the result of nearly 20 TWh of renewable energy curtailment. Utilizing this additional renewable energy curtailment for electrolytic hydrogen could produce 0.4 megatonnes of hydrogen and have 8.2 megatonnes of low-carbon benefit annually. © 2024, The Authors. All rights reserved.

关键词： Carbon

Metric Learning as a Service with Covariance Embedding

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kamal, Imam Mustafa Bae, Hyerim Liu, Ling The Institute of Intelligent Logistics Big Data Pusan National University 30-Jan-jeon Dong Geum-Jeong Gu Busan609-753 Korea Republic of The College of Computing Georgia Institute of Technology 266 Ferst Drive AtlantaGA30332-0765 United States Industrial Data Science & Engineering Department of Industrial Engineering Pusan National University 30-Jan-jeon Dong Geum-Jeong Gu Busan609-753 Korea Republic of

With the emergence of deep learning, metric learning has gained significant popularity in numerous machine learning tasks dealing with complex and large-scale datasets, such as information retrieval, object recognition and recommendation systems. Metric learning aims to maximize and minimize inter- and intra-class similarities. However, existing models mainly rely on distance measures to obtain a separable embedding space and implicitly maximize the intra-class similarity while neglecting the inter-class relationship. We argue that to enable metric learning as a service for high-performance deep learning applications, we should also wisely deal with inter-class relationships to obtain a more advanced and meaningful embedding space representation. In this paper, a novel metric learning is presented as a service methodology that incorporates covariance to signify the direction of the linear relationship between data points in an embedding space. Unlike conventional metric learning, our covariance-embedding-enhanced approach enables metric learning as a service to be more expressive for computing similar or dissimilar measures and can capture positive, negative, or neutral relationships. Extensive experiments conducted using various benchmark datasets, including natural, biomedical, and facial images, demonstrate that the proposed model as a service with covariance-embedding optimizations can obtain higher-quality, more separable, and more expressive embedding representations than existing models. © 2022, CC BY.

关键词： Embeddings

data-driven Industrial Robot Arm Calibration: A Machine Learning Perspective 18

学校读者我要写书评

暂无评论

Data-driven Industrial Robot Arm Calibration: A Machine Lear...

18th IEEE International Conference on Networking, Sensing and Control, ICNSC 2021

作者： Li, Zhibin Li, Shuai Luo, Xin University of Chinese Academy of Sciences School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing School Chongqing China Swansea University Department of Electronics and Electrical Engineering Swansea United Kingdom University of Chinese Academy of Sciences Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing School Chongqing China

ISBN: (纸本)9781665440486

Robot arms have been widely used in industry. The absolute positioning error of robots without calibration can reach several millimeters, which cannot meet the application requirements of accurate operation. Therefore, it is almost a mandatory procedure for industrial robots to take on-site calibration before being used. Generally, most researchers on robot calibration have mechanical and instrumentation background as the collection of calibration data is tedious and it is usually difficult to access to industrial robots for researchers in other fields. This research explores the calibration problem from a machine learning perspective and provides the first open-access dataset called "RobotCali"in this area so that machine learning scientists can step into this field and verify their algorithms on this problem. In the meanwhile, a new calibration method based on the Levenberg-Marquardt (LM) algorithm and extended Kalman filter (EKF) algorithm is proposed, which can significantly improve the absolute positioning accuracy of the robot after calibration. Firstly, the error model of robot is established, and kinematic parameters are initially identified by LM algorithm. Then the EKF algorithm is used to further calibrate these parameters, which has been verified the effectiveness of the proposed method by experimental results. Lastly, the future research work is discussed. © 2021 IEEE.

关键词： Calibration

Smoothed multi-view subspace clustering

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Peng Liu, Liang Ma, Zhengrui Kang, Zhao Jangsu Automation Research Institute Jiangsu Lianyungang China University of Electronic Science and Technology of China Sichuan Chengdu China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Sichuan Chengdu China

In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary imformation across multiple views. However, multi-view data can be very complicated and are not easy to cluster in real-world applications. Most existing methods operate on raw data and may not obtain the optimal solution. In this work, we propose a novel multi-view clustering method named smoothed multi-view subspace clustering (SMVSC) by employing a novel technique, i.e., graph filtering, to obtain a smooth representation for each view, in which similar data points have similar feature values. Specifically, it retains the graph geometric features through applying a low-pass filter. Consequently, it produces a "clustering-friendly" representation and greatly facilitates the downstream clustering task. Extensive experiments on benchmark datasets validate the superiority of our approach. Analysis shows that graph filtering increases the separability of classes. © 2021, CC BY-NC-ND.

关键词： Low pass filters

Stand-in Backdoor: A Stealthy and Powerful Backdoor Attack

学校读者我要写书评

暂无评论

Stand-in Backdoor: A Stealthy and Powerful Backdoor Attack

2021 IEEE Global Communications Conference (GLOBECOM)

作者： Shuang Li Hongwei Li Hanxiao Chen School of Computer Science and Engineering University of Electronic Science and Technology of China China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

ISBN: (纸本)9781728181059

Lack of transparency in deep learning models makes them vulnerable to backdoor attack, which can cause severe security consequences. For a backdoored model, the specific inputs can trigger misclassification rules while it performs normal behaviors on clean data. Existing backdoor attacks usually generate poisoned data by adding an obvious trigger to the original data and mislabeling them, which suffers from poor invisibility and hence can be easily detected. In this paper, we propose Stand-in Backdoor, a more stealthy and powerful backdoor attack, which can completely hide the trigger while maintaining correct labels of poisoned data. Specifically, we design a novel optimization strategy to transform triggers into imperceptible perturbation in the feature space. Furthermore, utilizing the transferability of feature perturbation, we fine-tune the victim model with well-constructed poisoned data that are correctly labeled. Extensive experiments conducted on various image classification tasks demonstrate that our attack outperforms the state-of-the-art work in terms of backdoor stealth and attack performance, without sacrificing the model's utility.

关键词： Perturbation methods Transforms Resists Manuals Inspection data models Security