检索结果-内蒙古大学图书馆

CustomFair: A Customized Fairness Method for Federated Recommender Systems in Social Internet of Things

IEEE Internet of Things Journal 2024年

作者： Chen, Guorong Li, Chao Du, Fei Yuan, Xiaohan Chi, Cheng Yin, Zihang Wang, Bin Li, Tao Bao, Xuhua Wang, Wei Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China China Academy of Information and Communications Technology Beijing China Network and Data Security Hangzhou310053 China Nankai University College of Computer Science Tianjin300350 China LTD Sangfor Technologies Co Beijing China Xi'an Jiaotong University Ministry of Education Key Lab for Intelligent Networks and Network Security Xi'an China

In the Social Internet of Things (SIoT), edge computing integrates artificial intelligence to learn intricate relationships. The scale and complexity of SIoT cause a data explosion from diverse objects, hindering tailored services to users who own objects. Moreover, conventional edge computing in SIoT depends on centralized data collection, raising concerns about data privacy. To address the above two issues, federated recommender systems (FRSs) present a promising solution. FRSs can provide SIoT services to users and train a shared model while retaining sensitive data locally on objects. However, as FRSs are driven by data, they are inherently susceptible to algorithmic bias, raising substantial fairness concerns that have attracted considerable attention in SIoT. Recent fairness studies predominantly concentrate on a single sensitive attribute for users, thereby overlooking their autonomy. Therefore, we propose CustomFair, a personalized fairness framework that enables users in FRSs to select preferred sensitive attributes and acquire satisfied recommendation services in SIoT scenarios. First, we define customized fairness to ensure group fairness based on users' sensitive attributes. The server segments users into subgroups in a privacy-preserving manner. Second, CustomFair employs the DynBalance method with a flexible regularization coefficient to improve recommendation performance and utilizes the AdaptEpoch strategy to achieve fairness. Extensive experiments indicate that CustomFair improves recommendation performance by 0.1 ∼ 42.92 and enhances fairness by reducing disparities of 0.03 ∼ 5.41 compared to two baselines across three datasets. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Feature Selection Method Based on FSA-Choquet Fuzzy Integral

Feature Selection Method Based on FSA-Choquet Fuzzy Integral

引用

Industrial IoT, Big Data and Supply Chain (IIoTBDSC), International Conference on

作者： Zhangyu Xu Huaijun Wang Ruijie Wang Junhuai Li Xunchao Shang School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China

With the instant development and wide application of sensor technology, human behavior recognition based on wearable sensors has attracted wide attention and become a hot research topic. The typical Choquet fuzzy integral feature selection method considers the interaction between classes, but the preferred features are not tested in the feature selection process. The selected feature subset is not suitable for different classifiers and different classification actions, and there are redundant features. Consequently, this paper proposes an adaptive feature selection method named Feature Selection based on the Adaptive Choquet fuzzy integral (FSA-Choquet). This proposed method can get the optimal subset by two times of feature selections. First, Choquet fuzzy integral is applied to optimize the current optimal feature subset. Then the feature selection is processed by combining the maximum redundancy calculation with the backward floating search strategy and classifier. At last, Experiments show that the feature based on FSA-Choquet selection has a higher classification recognition rate in behavior recognition. Under the comparison based on SVM classifier, the recognition accuracy of the features selected by FSA-Choquet is as high as 89.6 %, and the recognition rate of the features selected by Choquet is 77.36 %. Besides, Under the classifier based on Naive Bayes (NB), the classification recognition rate of FSA-Choquet is 91.67 %, while that of Choquet is only 82.3 %.

关键词： Support vector machines Redundancy Supply chains Diversity reception Big Data Feature extraction Search problems

来源：评论

学校读者我要写书评

暂无评论

A security Enhancement Scheme For Raft Consensus Algorithm Against Term Forgery Attacks

A Security Enhancement Scheme For Raft Consensus Algorithm A...

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yichuan Wang Mengjie Tian Yaling Zhang Xiaoxue Liu Yeqiu Xiao Xinhong Hei School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China

The consensus algorithm is the core component of blockchain technology and a key link to maintaining the security of the blockchain network. In the Raft consensus algorithm, since the term growth range is not specified in the algorithm, malicious nodes can obtain the leader status by increasing their term value, and the fairness of the Raft cluster leader election is damaged. To solve the above problems, in this paper, we restore the attack experiment, which is a malicious node gaining leader status by increasing its term value. Identify malicious nodes by dynamically adjusting the growth range of the term, thus achieving a defensive effect. The optimized algorithm resists malicious node attacks with a 79.4% probability and reduces the election time by 11.4% compared to the Raft consensus algorithm in the presence of malicious nodes. On the premise of ensuring high efficiency, the fault tolerance and security of the algorithm have also been significantly improved.

关键词： Fault tolerance Voting Fault tolerant systems Clustering algorithms Consensus algorithm Resists Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Cross-chain Jamming Attack with Light Client Verification Clash in IBC Protocol

Cross-chain Jamming Attack with Light Client Verification Cl...

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Yaling Zhang Ziyan Wang Yichuan Wang Xiaoxue Liu Xinhong Hei School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China

Inter-Blockchain Communication (IBC) in Cosmos is a Sidechains/Relays cross-chain protocol. During the implementation of the protocol, the blockchain uses relayers to establish connections, and uses light clients to track and verify the consensus state of counterparties. However, light clients lack effective malicious behavior detection mechanisms, which easily induces the effective attacks to cross-chain communication. This paper proposes a light client jamming attack in IBC cross-chain protocol. Attackers force the victim’s light client to be in the verification state frequently by continuously generating headers containing a large number of verifier signatures. By interfering with light clients, attackers can reduce the victim’s cross-chain transaction throughput with low cost and increase the probability of cross chain transaction failure. Based on the Cosmos blockchain, this paper tests the attack, models the attack process and analyzes its security. The experiment shows that when the header constructed by the attacker contains $5.0\times 10^{4}$ signatures, the probability of successful attack can reach 90%. Finally, this paper briefly introduces some feasible defense strategies against this attack.

关键词： Analytical models Protocols Costs Force Formal languages Throughput Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Prompt and Contrastive Learning for Few-shot Sentiment Classification 22

Prompt and Contrastive Learning for Few-shot Sentiment Class...

引用

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

作者： Fei Wang Long Chen Xiaohua Huang Cai Xu Wei Zhao Ziyu Guan Guangyue Lu Shaanxi Key Laboratory of Information Communication Network and Security Xi'an University of Posts and Telecommunications China School of Information Science and Technology Northwest University China School of Computer Science and Technology Xidian University China

ISBN: (纸本)9781450396899

Sentiment classification is a hot topic in the field of natural language processing. Currently, state-of-the-art classification models follow two steps: pre-training a large language model on upstream tasks, and then using human-labeled data to fine-tune a task-related model. However, there is a large gap between the upstream tasks of the pre-trained model and the downstream tasks being performed, resulting in the need for more labeled data to achieve excellent performance. Manually annotating data is expensive. In this paper, we propose a few-shot sentiment classification method based on Prompt and Contrastive Learning (PCL), which can significantly improve the performance of large-scale pre-trained language models in low-data and high-data regimes. Prompt learning aims to alleviate the gap between upstream and downstream tasks, and the contrastive learning is designed to capture the inter-class and intra-class distribution patterns of labeled data. Thanks to the integration of the two strategies, PCL markedly exceeds baselines with low resources. Extensive experiments on three datasets show that our method has outstanding performance in the few-shot settings.

关键词： Contrastive learning Prompt learning Sentiment classification

来源：评论

学校读者我要写书评

暂无评论

Pervasive Container Computing–––a Fine-Grained Loosely Coupled Cloud Cluster

Pervasive Container Computing–––a Fine-Grained Loosely Co...

引用

IEEE International Symposium on Parallel and Distributed Processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Xinhong Hei Dan Wu YiFan Liu Wenjiang Ji Yichuan Wang Lei Zhu School of computer science and engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China

With the emergence of CaaS, a cloud service model that can quickly build a production environment, this model has been widely used in the industry. However, the degree of loose coupling of various containers in the cluster and the fine-grained level of function division are often difficult to achieve people’s expectations. In addition, it is difficult to achieve the desired effect in terms of cloud cluster security. Therefore, this paper takes container-based cloud computing clusters as the main research object, and proposes a fine-grained, loosely coupled cloud cluster model based on containers, is called Pervasive-container computing. The experimental results show that Pervasive-container computing not only meets the fine-grained loose coupling characteristics required by microservices, but also adopts the strategy of “created with time” and “destroy after use”, which provides guarantees in terms of endogenous security. In addition, the proposed scheduling algorithm based on Pervasive-container calculation reduces the time consumption of file transfer by 20% compared to the time consumption without the algorithm.

关键词： Couplings Industries Cloud computing Scheduling algorithms Computational modeling Microservice architectures Production

来源：评论

学校读者我要写书评

暂无评论

News-driven financial warning based on label information attention 22

News-driven financial warning based on label information att...

引用

Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition

作者： Ren Zhilin Chen Long Huang Xiaohua Wang Wenjing Xu Cai Zhao Wei Guan Ziyu Shaanxi Key Laboratory of Information Communication Network and Security Xi'an University of Posts and Telecommunications China School of Information Science and Technology Northwest University China School of Computer Science and Technology Xidian University China

ISBN: (纸本)9781450396899

Most existing news-driven stock market prediction methods ignore the potential relationship between financial news and stocks. The complex relationship can help us to improve the accuracy of algorithmic trading systems. Therefore, we propose a deep learning method for financial warning by fusing Stock label Information (SLI). We extract events from news texts and fuse stock information together as feature vectors, using neural networks to model the underlying relationship between news and stocks. Experimental results show that our method outperforms other baseline methods in experiments on TPX500 and TPX100 *** CONCEPTS • Computing methodologies • Artificial intelligence • Natural language processing

关键词： Deep learning Financial warning News-driven Stock label information

来源：评论

学校读者我要写书评

暂无评论

DHD: Double Hard Decision Decoding Scheme for NAND Flash Memory

DHD: Double Hard Decision Decoding Scheme for NAND Flash Mem...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Lanlan Cui Yichuan Wang Renzhi Xiao Miao Li Xiaoxue Liu Xinhong Hei School of Computer Science and Engineering XI'AN University of Technology Xi'an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China School of Software Engineering Jiangxi University of Science and Technology Nanchang China School of Information Engineering Zhongnan University of Economics and Law Wuhan China

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

With the advancement of NAND flash technology, the increased storage density leads to intensified interference, which in turn raises the error rate during data retrieval. To ensure data reliability, low-density parity-check (LDPC) codes are extensively employed for error correction in NAND flash memory. Although LDPC soft decision decoding offers high error correction capability, it comes with a significant latency. Conversely, hard-decision decoding, although faster, lacks sufficient error correction strength. Consequently, flash memory typically initiates with hard-decision decoding and resorts to multiple soft decision decoding upon failure. To minimize decoding latency, this paper proposes a decoding mechanism based on the double hard decision, called DHD. This DHD scheme improves the Log-Likelihood Ratio (LLR) in the hard decision process. After the first hard decision fails, the read reference voltage (RRV) is adjusted to perform the second hard decision decoding. If the second hard decision also fails, soft decision decoding is then employed. Experimental results demonstrate that when the Raw Bit Error Rate (RBER) is $8.5 \times 10^{-3}$ , DHD reduces the Frame Error Rate (FER) by 86.4% compared to the traditional method.

关键词： Lead acid batteries Europe Voltage Interference Decoding Error correction Error correction codes Reliability Flash memories Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Poisoning Attacks and Defenses to Learned Bloom Filters for Malicious URL Detection

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Dong, Fangming Wang, Pinghui Li, Rundong Cui, Xueyao Zhao, Junzhou Tao, Jing Zhang, Chen Guan, Xiaohong Zhejiang CreateLink Technology Co. Ltd Guangdong Guangzhou China Xi'an Jiaotong University MOE Key Laboratory for Intelligent Networks and Network Security Shaanxi Xi'an710049 China Tsinghua University Center for Intelligent and Networked Systems Tsinghua National Lab for Information Science and Technology Beijing China

Approximate membership query (AMQ) structures represented by the Bloom Filter and its variants have been popularly researched in recent years. Researchers have recently combined machine learning with this type of structure to reduce space consumption and computation overhead further and make remarkable progress. However, with the booming performance in space or other metrics, researchers tend to ignore the security of the trained model. The machine learning model is vulnerable to poisoning attacks, and naturally, we infer that the learning-based filters also have the same deficiencies. Hence, in this paper, to confirm the inference mentioned above, experiments on the real-world datasets of URLs are conducted and prove that it is necessary to consider the security issue when using learning-based filters. We show that by data poisoning, the attacker can deflect learned Bloom Filters to make a false identification, which can lead to a significant loss in some cases. Aiming to solve this issue, we put forward a method named Defensive Learned Bloom Filter (DLBF) to diminish the influence of data poisoning and achieve a better performance compared to types of learned Bloom Filters. © 2004-2012 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

A Quantum Temporal Difference Learning Method Based on Quantum World Model

A Quantum Temporal Difference Learning Method Based on Quant...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Peigen Zeng Ying He F. Richard Yu Jianbo Du College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts and Telecommunications Xi’an China School of Information Technology Carleton University Ottawa Canada

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Based on quantum parallelism theory and quantum phenomena such as superposition and entanglement, quantum reinforcement learning (QRL) has the potential to surpass classical reinforcement learning (RL). Although some excellent works have been done on QRL, existing RL methods encounter chanllenges when performing in environments with sparse rewards. In this paper, we provide a new perspective on conducting temporal difference (TD) learning in quantum computing, which can eliminate redundant exploration steps compared to classical methods. Specifically, we first use environment information to construct a world model with quantum circuits, enabling it to interact in a quantum way. Then, we perform the learning process by using the quantum world model and Grover’s algorithm to query backwards how to reach the recorded states with high TD-errors. Simulation results show that our proposed method has superior performance compared to classical RL algorithms.

关键词： Quantum entanglement Computational modeling Simulation Temporal difference learning Parallel processing Global communication Integrated circuit modeling Quantum circuit

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：