检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on Zero-Trust Architecture, Application Areas & Challenges of 6G Technology in Future

Study on Zero-Trust Architecture, Application Areas & Challe...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Richa Singh Gaurav Srivastav Rekha Kashyap Satvik Vats Computer Science & Engineering (AI) Krishna Group of Institutions Ghaziabad India Artificial Intelligence & Data Science Datta Meghe Institute of Higher Education & Research Maharashtra India Computer Science & Engineering Graphic Era Hill University Dehradun India

Intelligent network orchestration and management are crucial components of the 6G network. Therefore, machine learning and artificial intelligence play a big part in the 6G paradigm that is being imagined. However, the combination of 6G and AIML utilization may frequently be a double-edged sword because AI has the capacity to either protect or compromise security and privacy. Proactive threat detection, the use of mitigating intelligent techniques, and network automation in future are needed to enable the achievement of independent networks in 6G. As a result, this paper has detailed focus on the ongoing projects based on 6G and factors that make 6G technology necessary. The role of ZT architecture is discussed in detail, use of AIML in 6G, Various application areas and challenges associated in 6G has been mentioned in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects

arXiv

引用

arXiv 2024年

作者： Li, Na Zhou, Chunyi Gao, Yansong Chen, Hui Fu, Anmin Zhang, Zhi Yu, Shui School of Cyberspace Science and Engineering Nanjing University of Science and Technology Nanjing210094 China State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Data61 CSIRO CanberraACT2601 Australia Department of Computer Science and Software Engineering University of Western Australia PerthWA6009 Australia School of Computer Science University of Technology Sydney SydneyNSW2007 Australia

Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. data users have been endowed with the 'right to be forgotten' of their data. In the course of machine learning (ML), the forgotten right requires a model provider to delete user data and its subsequent impact on ML models upon user requests. Machine unlearning emerges to address this, which has garnered ever-increasing attention from both industry and academia. While the area has developed rapidly, there is a lack of comprehensive surveys to capture the latest advancements. Recognizing this shortage, we conduct an extensive exploration to map the landscape of machine unlearning including the (fine-grained) taxonomy of unlearning algorithms under centralized and distributed settings, debate on approximate unlearning, verification and evaluation metrics, challenges and solutions for unlearning under different applications, as well as attacks targeting machine unlearning. The survey concludes by outlining potential directions for future research, hoping to serve as a guide for interested scholars. Copyright © 2024, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

A Pre-selected Local Weighted Method for Improving the Performance of LMKNN Classifier

A Pre-selected Local Weighted Method for Improving the Perfo...

引用

IEEE International Conference on Power, Intelligent Computing and Systems (ICPICS)

作者： Yuzhi Zhang Ziyan Guan Chen Xiong School of Aeronautic Science and Engineering Beihang University Beijing China School of Big Data & Software Engineering Chongqing University Chongqing China School of Computer Science Xi'an Jiaotong University City College Xi'an China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

The K-nearest neighbor (KNN) algorithm and its variant Local Mean K-nearest neighbor (LMKNN) have been widely used in the field of data mining due to their simplicity and intuition. However, these methods have limitations when dealing with unbalanced datasets and edge samples, such as sensitivity to the choice of nearest neighbor size and degradation of classification performance for outlier points. To address these issues, this paper proposes a pre-selected locally weighted mean K-nearest neighbor (PLWMKNN) algorithm, which aims to improve the performance of LMKNN through an advanced pre-selection mechanism and a weighted average method. PLWMKNN firstly pre-selects favorable classes as the nearest neighbors based on the distance weights, and then computes the weighted center vectors of each class to classify them by the minimum distance principle. Through experimental validation on four real datasets, PLWMKNN shows significant performance improvement over traditional KNN and LMKNN for unbalanced datasets. Our results demonstrate the effectiveness of the PLWMKNN algorithm in improving classification accuracy and robustness, especially when dealing with extremely unbalanced datasets.

关键词： Degradation Accuracy Sensitivity Image recognition Text categorization Nearest neighbor methods Vectors Robustness Classification algorithms data mining

来源：评论

学校读者我要写书评

暂无评论

Extended Finite State Machine based Fault Tolerance in WSN

Extended Finite State Machine based Fault Tolerance in WSN

引用

International Conference on Computing Methodologies and Communication (ICCMC)

作者： D. Lekha Ahsan Shariff M S. Venkata Lakshmi Anwar Basha H Department of Computer Science and Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Aalim Muhammed Salegh College of Engineering Chennai Tamil Nadu India Artificial Intelligence and Data Science Sri Krishna College of Engineering and Technology Coimbatore Tamil Nadu India School of Computer Science And Engineering REVA University Bengaluru Karnataka India

Wireless Sensor Network (WSN) suffers from different malware attacks. Several traditional approaches are proposed for detecting fault nodes in WSN. It is necessary to redistribute the nodes and detect the fault nodes while modifying the WSN parameters. Faults can occur in the nodes interrupting the continuous communication process of the nodes in the WSN. The main reason for a fault is also the induction of the energy drain in a node to the maximum possible level, failure of links in communicating nodes due to bandwidth constraints, and attacks induced by the malicious nodes. To solve this problems, Extended Finite State Machine based Fault Tolerance (EFSM_FT) in the WSN is used to detect the fault sensor nodes in the WSN. In this approach, called the finite state machine (FSM), state prompted is modified while a set of situations are true. Every node can be absolutely to be faulty or not establishing on the sensor node states. Using sensor energy, drop rate, forward sensor rate, sensor obtained rate, bandwidth, and transmission delay, this method finds the node with the fault. As a result, this approach accurately detects the faulty nodes in the WSN. The simulation outcomes illustrate the proposed method has a better fault detection ratio and minimizes the false negative ratio in the WSN.

关键词： Fault diagnosis Wireless sensor networks Fault tolerance Fault detection Computational modeling Fault tolerant systems Automata

来源：评论

学校读者我要写书评

暂无评论

MalDIST: From Encrypted Traffic Classification to Malware Traffic Detection and Classification 19

MalDIST: From Encrypted Traffic Classification to Malware Tr...

引用

19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022

作者： Bader, Ofek Lichy, Adi Hajaj, Chen Dubin, Ran Dvir, Amit Ariel Cyber Innovation Center Ariel University Department of Computer Science Ariel Israel Ariel Cyber Innovation Center Ariel University Data Science and Artificial Intelligence Research Center Department of Industrial Engineering & Management Ariel Israel

ISBN: (纸本)9781665431620

The world of malware is shifting towards using encrypted traffic. While encryption improves the privacy of users, it brings challenges in the fields of QoS, QoE, and cybersecurity. Recent state-of-the-art Deep-Learning architectures for encrypted traffic classifications demonstrated superb results in tasks of traffic categorization over encrypted traffic. In this paper, we leverage the feasibility to use such architectures for the tasks of malware detection and classification to gain insights into how well these architectures perform in the domain of malware traffic. Specifically, we present a Deep-Learning model for malware traffic detection and classification (MalDIST), which outperforms both classical ML and DL malware traffic classification models both in terms of detection and classification. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Earthquake Damage Prediction and Rapid Assessment of Building Damage Using Deep Learning

Earthquake Damage Prediction and Rapid Assessment of Buildin...

引用

Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS), International Conference on

作者： Yuvaraj Natarajan Gitanjali Wadhwa Preethi Akshaya Ranganathan Karthika Natarajan Dept. of Computer Science and Engineering KPR Institute of Engineering and Technology Coimbatore India Dept. of Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India

One of the most expensive natural disasters that affect people, earthquakes occur suddenly. As a result, earthquake prediction has grown in importance and difficulty for humanity. Although numerous existing approaches attempt to handle this problem, the majority rely on seismic indicators created by geologists or feature vectors extracted by the deep learning techniques to describe an earthquake for the earthquake prediction. Combining these two categories of characteristics to enhance ultimate Earthquake prediction performance is still a challenge. In order to achieve this, we put forth a deep learning model that successfully fuses explicit and implicit information for earthquake prediction. Here, we use a Convolutional Neural Network to extract implicit features while using eight precursory pattern-based indicators as the explicit features. After that, an attention-based approach is suggested to effectively combine these two categories of traits. A dynamic loss function is the additionally created to address the imbalance of category in seismic data. On a test picture dataset, the performances of multiple CNN models are contrasted. In order to classify earthquake damage, the model is further developed as a web application. Damage assessment values, which are determined using the Convolutional Neural Network model and gradient-weighted class activation mappings, are used to determine the extent of the damage. The web-based program can efficiently and automatically categorize earthquake-related structural damage, making it appropriate for decision-making in emergency response, resource allocation, and policy formation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Maximum Effort Consensus Modeling Under Social Network Considering Individual Emotions 22nd

Maximum Effort Consensus Modeling Under Social Network Consi...

引用

22nd International Symposium on Knowledge and Systems sciences, KSS 2023

作者： Xu, Mengru Jing, Fuying Chao, Xiangrui Herrera-viedma, Enrique School of Management Science and Engineering Chongqing Technology and Business University Chongqing400067 China National Research Base of Intelligent Manufacturing Service Chongqing Technology and Business University Chongqing400067 China School of Business Sichuan University Chengdu610065 China Andalusian Research Institute in Data Science and Computational Intelligence Department of Computer Science and Artificial Intelligence University of Granada Granada18071 Spain

ISBN: (纸本)9789819983179

It’s beyond disputed that everyone has their own unique understandings of words, which induces personalized individual semantics (PISs) attached to linguistic expressions. Social network illustrates trust relationships among group members. In linguistic social network decision making (SNGDM), social network analysis usually aids in determining the importance weights of decision makers (DMs). Actually, emotions may have an impact on trust propagation. For instance, positive emotions would strengthen trust whereas negative emotions work in a reverse way. Thus, a social network with individual emotions is firstly developed. Generally, DMs are frequently required to modify their opinions in consensus reaching process (CRP). To some extent, emotions also reflect their adjusted probabilities. Meanwhile, DM’s willingness and attitude to making necessary modifications for better agreement, that is measured by effort degree, will bring to different consensus results. Under a limited cost budget, a maximum effort consensus model driven by maximizing all DMs’ effort degree is proposed for instructing feedback regulation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Applying Machine Learning to Strengthening Cyber Security

Applying Machine Learning to Strengthening Cyber Security

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： M. Vigenesh M Shalini P Mandar Inzimam Ul Hassan Sukhvinder Singh Dari S. Annamalai Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Technology Pune INDIA Department of Computer Science & Engineering Vivekananda Global University Jaipur India Symbiosis Law School Nagpur Symbiosis International (Deemed University) Pune India School of Computer Science and Engineering Jain (Deemed to be University) Bangalore Karnataka India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Cyber safety threats have become a central problem in the contemporary world, with hackers constantly finding new approaches to make the most systems and users to gain unauthorized admission. Gadget learning has been determined to be a promising approach to combat these threats, considering the improvement of state-of-the-art algorithms capable of detecting malicious activities in near real-time. Through supervised studying, neural networks, or other sample popularity techniques, these algorithms can learn how to locate malicious conduct and lift an alert to take appropriate countermeasures. Additionally, device getting to know can be used to identify new threats and recognize formerly unknown flaws in present defenses, allowing them to be patched or upgraded promptly. Given the ever-converting nature of the cyber security landscape, gadget studying programs are worthwhile for staying ahead of the curve and retaining information secure.

关键词： Security management Neural networks Machine learning Reconnaissance Real-time systems Hazards Object recognition computer crime Protection Testing

来源：评论

学校读者我要写书评

暂无评论

A Novel Intelligent AI-Based Security to Enhance the data Communication: An Empirical Review

A Novel Intelligent AI-Based Security to Enhance the Data Co...

引用

International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2022

作者： Shaik, Amjan Hung, Bui Thanh Chakrabarti, Prasun Siva Shankar, S. Parveen, Nikhat Department of Computer Science and Engineering Dean R&D St. Peter’s Engineering College Maisammaguda Telangana Hyderabad India Data Science Laboratory Faculty of Information Technology Industrial University of Ho Chi Minh Ho Chi Minh Viet Nam Department of Computer Science and Engineering Sir Padampat Singhania University Rajasthan Udaipur India Adjunct Distinguished Professor ITM SLS Baroda University Gujarat Vadodara India CSE K G Reddy College of Engineering and Technology Moinabad India CSE Koneru Lakshmaiah Education Foundation AP Guntur Vaddeswaram India

ISBN: (纸本)9789819947164

The transmission of digital data between two devices is termed data communication. As the world nowadays relies on digital communication, the transferring of data among various devices is vitally important, and hence, the security of the data is a concern. Several works are carried out to secure the data transmission between the devices in various applications like mobile communication, wireless communication, vehicular communication, and more. Incorporated with security, the data classification is also performed to ignore the unwanted or hackers’ data. In this work, we have discussed several secure data communication-related papers from various applications. Works including machine learning-based approaches such as decision tree, linear regression, logistic regression, KNN, K-means, and deep learning-based approaches such as a convolutional neural network, recurrent neural network, and long short-term memory approaches were discussed and listed with their limitations along with merits. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decision trees

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：