检索结果-内蒙古大学图书馆

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Guo, Jinyuan Sun, Lijuan Wu, Jingchen Chu, Chiawei Gao, Yutong Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China School of Cybersecurity Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance Ministry of Education Minzu University Beijing China Intellectual Property Information Service Center BHU Beihang University Beijing China City University of Macau Taipa China Li’an International Education Innovation Pilot Zone Hainan International College of Minzu University of China Hainan Beijing China

ISBN: (纸本)9789819615278

Proof of Data Possession is a technique for ensuring the integrity of data stored in cloud storage. However, most audit schemes assume only one role for data owners, which is not suitable for complex Smart Healthcare Network with multiple roles. In such schemes addressing the risk of third-party auditors (TPA) colluding with other entities, blockchain is typically employed. However, this necessitates extensive computation, resulting in unacceptably high energy consumption and prolonged verification times. In this paper, we propose a Proof of Data Possession scheme tailored for medical network environments, which incorporates protocols designed for both healthcare professionals and patients, considering the diverse roles that generate data within medical network applications and the varying performance of the devices they use. During the generation of metadata for verification, the protocol incorporates the varying security risk levels associated with medical data. For subsequent metadata selection, an audit block extraction strategy based on strange attractors is employed, effectively mitigating the risk of collusion by third-party TPA, thereby enhancing the security and efficiency of the scheme. Additionally, we conducted experimental analysis and comparisons, demonstrating higher security and practical applicability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

On the Calibration of Large Language Models and Alignment

arXiv

引用

arXiv 2023年

作者： Zhu, Chiwei Xu, Benfeng Wang, Quan Zhang, Yongdong Mao, Zhendong University of Science and Technology of China Hefei China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China

As large language models attract increasing attention and find widespread application, concurrent challenges of reliability also arise at the same time. Confidence calibration, an effective analysis method for gauging the reliability of deep models, serves as a crucial tool for assessing and improving their reliability. However, such investigation has been comparatively underexplored. In this work, we conduct a systematic examination of the calibration of aligned language models throughout the entire construction process, including pretraining and alignment training. At each stage, we investigate how different training settings, such as parameter scales and training data, affect model calibration. To thoroughly assess model calibration, we evaluate models on three most concerned aspects: generation, factuality and understanding. Our work sheds light on whether popular LLMs are well-calibrated and how the training process influences model calibration. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Joined CNN and transformer network for thorax disease classification 5

Joined CNN and transformer network for thorax disease classi...

引用

5th International Conference on Artificial Intelligence and Computer Science, AICS 2023

作者： Zhang, Ruihua Chen, Wenkai Liu, Wenjia Beijing University of Posts and Telecommunications Beijing100876 China Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing100876 China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China Department of Radiology Chinese PLA General Hospital Beijing100853 China

ISBN: (纸本)9781510668621

Thorax disease classification is a complex problem due to lesions are scattered and different diseases are related. It will benefit the diagnosis to comprehensively analyze the context of the scattered lesions and multiple diseases. Most existing supervised methods use Convolutional Neural Networks (CNNs) to capture chest X-ray (CXR) features for classification, but usually ignore the context representation which is useful for multi-label classification tasks. In this paper, we propose a novel thorax disease classification network with joined CNN and Transformer (TC-CNNT) that learns global features and context representations simultaneously. Specifically, TC-CNNT includes a CNN branch to gradually extract global feature representations from low-level to high-level through convolutional filtering. Meanwhile, a transformer branch is designed to capture context-dependent features through the self-attention mechanism of the shift windows. In addition, the feature fusion and multi-loss strategy are applied to maximumly learn the complementary global and context representations. Finally, the TC-CNNT method is verified on the ChestX-ray14 dataset and compared with the state-of-the-art methods, the experimental results demonstrate its superior performance for thorax disease classification. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Reliable Blockchain-based Trust Management Model for Electricity Trading Terminal

引用

Journal of Computers (Taiwan) 2023年第3期34卷 251-271页

作者： Liu, Zhenzhen Zhou, Rui Huang, Kangqian Hu, Xin Deng, Kaiyang Cai, Binsi Yuan, Kaiguo Information Data Department Guangdong Power Exchange Center Co. Ltd. Guangdong510080 China A Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing100876 China

A safe and reliable terminal environment is crucial to ensure the security of the electricity trading system. The existing terminal security system based on identity authentication and access control has internal threats that are difficult to solve. For example, multiple internal malicious nodes cause broadcast message tampering attacks and malicious packet loss, resulting in message dissemination failure. Existing blockchain- based trust management systems are good for addressing insider threats, but suffer from low efficiency. In order to solve the internal threat problem of the electric electricity trading system, from the perspective of trust evaluation and trust management of the terminal environment, an efficient and reliable blockchain-based electric trading terminal (ERBTM) trust management model is proposed. First of all, we collect a variety of trust factors to evaluate the credibility of the terminal, which solves the problem of accuracy in the process of trust assessment;secondly, we improve the speed of storing trust values on the chain and ensure the robustness of the system by improving the consensus algorithm;Finally, we designed the structure of the block that stores the trust value to ensure that the trust value is not tampered with. The experimental results show that, compared with similar methods, the ERBTM model can effectively deal with the endogenous security threats of terminals in the electricity trading environment, and has significant advantages in terms of efficiency and reliability. © 2023 Computer Society of the Republic of China. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Based on Feature Reduction and Model Pruning in Electricity Trading Network

引用

Journal of Computers (Taiwan) 2023年第5期34卷 213-227页

作者： Liu, Zhenzhen Zhou, Rui Huang, Kangqian Hu, Xin Jiang, Zhe Cai, Binsi Yuan, Kaiguo Information Data Department Guangdong Power Exchange Center Co. Ltd. Guangdong510080 China A Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing100876 China

The electricity trading network increases network flexibility and lowers trading costs with the aid of 5G and IOT technology. While it has improved trading efficiency and enhanced system intelligence, its security vulnerabilities pose significant challenges. In this study, we propose an intrusion detection method that focuses on feature reduction and model pruning in electricity trading network. The method effectively addresses the imbalance issue of the IDS2017 dataset by employing the SMOTE algorithm, reduces feature size and computational complexity through the application of PCA, autoencoder, and random forest techniques, and develops a lightweight intrusion detection model specifically designed for electricity trading network using model pruning and compression techniques. Experimental results demonstrate the effectiveness of the proposed model in detecting intrusions. The achieved precision, recall, F1 score, and false positive rate are at least 98.8%, 87.9%, 90.0%, and 0.08%, respectively. Furthermore, we conducted a comparative analysis of different pruning thresholds and determined that reducing the dimensionality to 49 dimensions yields superior model performance, making it particularly suitable for resource-constrained electricity trading network. © 2023 Computer Society of the Republic of China. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual Propaganda Detection

Cross-Lingual Propaganda Detection

引用

IEEE International Conference on Big Data

作者： Wenshan Zhang Xi Zhang Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781665480468

Propaganda information that aims at influencing people’s opinions is becoming more and more common around people, especially through social media. For the detection of propaganda content, researchers have conducted studies from multiple perspectives, including document level, sentence level and fragment level. However, most existing methods have mainly focused on propaganda detection in a single language because of the lack of multilingual datasets. In this article, we first propose a Chinese and English propaganda detection dataset. Then we propose a cross-lingual propaganda detection method, using semantic and syntactic information between different languages. Extensive experiments on our multilingual dataset demonstrate the effectiveness of our proposal in cross-lingual propaganda detection.

关键词： Social networking (online) Fuses Semantics Syntactics Big Data Transformers Information filters

来源：评论

学校读者我要写书评

暂无评论

An Efficient Batch Verification Scheme for SM2 Signatures 8

An Efficient Batch Verification Scheme for SM2 Signatures

引用

8th International Conference on Dependable Systems and Their Applications, DSA 2021

作者： Liu, Dingning Yuan, Yuyu Xue, Tengfei Chen, Lei Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education China Huawei Technologies Co. Ltd China

ISBN: (纸本)9781665443913

SM2 cryptographic algorithm is an elliptic curve public key algorithm released by China's State Cryptography Administration, which includes digital signature algorithms, key exchange protocols, public key encryption algorithms, etc. As SM2 is widely used in identity authentication and authorization services in scenarios such as e-government, e-commerce and national economy, we found that there is less research on batch verification scheme for SM2 signatures to improve the performance of multi-verification tasks. In this paper, we provide an efficient batch verification scheme for SM2 signatures which is based on the public key verification and calculation of original algorithm. Different from single verification at a time, it can improve the calculation speed by verifying multiple signatures together. Aiming at the possibility of future use in industrial applications, we then provide a highly available implementation of the algorithm. Also, we discuss the verification performance for different quantity of signers and signatures. © 2021 IEEE.

关键词： Electronic document identification systems

来源：评论

学校读者我要写书评

暂无评论

An Efficient Active Learning based Method for Deepfake Vidoes Model Attribution

An Efficient Active Learning based Method for Deepfake Vidoe...

引用

Digital Society and Intelligent Systems (DSInS), International Conference on

作者： Xiaotian Si Weiqiang Jiang Linghui Li Xiaoyong Li Kaiguo Yuan Zhongyuan Guo Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications Beijing China Chine Mobile Group Co. Ltd Beijing China

To enhance the forensic investigation of deepfake face-swap videos, it is essential to attribute the specific generation model used to create these videos. Despite the remarkable progress made in data-driven approaches, recent algorithms continue to encounter challenges in learning from limited annotated data, thereby limiting their performance. In this paper, we present a novel active learning framework for the model attribution of deepfake videos. Specifically, our approach leverages active learning to select the most informative videos, thereby effectively reducing the annotation effort. To achieve this, we propose a query function based on clustering, where the clustering features are generated by a projection network trained through supervised contrastive learning. Extensive experiments demonstrate that our method achieves state-of-the-art performance in model attribution of deepfake videos, surpassing other baseline methods in the field of active learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Trade less Accuracy for Fairness and Trade-off Explanation for GNN

Trade less Accuracy for Fairness and Trade-off Explanation f...

引用

IEEE International Conference on Big Data

作者： Yazheng Liu Xi Zhang Sihong Xie Key Laboratory of Trustworthy Distributed Computing and Service (MoE) BUPT Computer Science and Engineering Dept Lehigh University

ISBN: (纸本)9781665480468

Graphs are widely found in social network analysis and e-commerce, where Graph Neural Networks (GNNs) are the state-of the-art model. GNNs can be biased due to sensitive attributes and network topology. With existing work that learns a fair node representation or adjacency matrix, achieving a strong guarantee of group fairness while preserving prediction accuracy is still challenging, with the fairness-accuracy trade-off remaining obscure to human decision-makers. We first define and analyze a novel upper bound of group fairness to optimize the adjacency matrix for fairness without significantly h arming prediction accuracy. To understand the nuance of fairness-accuracy tradeoff, we further propose macroscopic and microscopic explanation methods to reveal the trade-offs and the space that one can exploit. The macroscopic explanation method is based on stratified sampling and linear programming to deterministically explain the dynamics of the group fairness and prediction accuracy. Driving down to the microscopic level, we propose a path-based explanation that reveals how network topology leads to the tradeoff. On seven graph datasets, we demonstrate the novel upper bound can achieve more efficient fairness-accuracy trade-offs and the intuitiveness of the explanation methods can clearly pinpoint where the trade-off is improved.

关键词： Training Upper bound Network topology Social networking (online) Microscopy Big Data Linear programming

来源：评论

学校读者我要写书评

暂无评论

Introducing Natural Language-based Instruction Protocol for Intelligent Machine Collaborations

Introducing Natural Language-based Instruction Protocol for ...

引用

International Wireless Communications and Mobile computing Conference, IWCMC

作者： Haobing Gong Hui Gao Yuting Feng Caixia Yuany Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Information and Communication Engineering School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China

The rapid development of various autonomous unmanned systems has increased the endogenous intelligence of machines, which empowers functional collaborations among intelligent machines. However, traditional protocols for intelligent machine collaboration have limitations regarding functionality, efficiency, and scalability. Moreover, existing research on intelligent machine collaboration is not yet approaching a unified paradigm that facilitates interactions among machines and between machines and humans. Therefore, aiming to enable a more efficient functional collaboration among intelligent machines, we propose a natural language-based instruction (NLI) protocol, which enjoys the advantages of autonomy, robustness and efficiency. In particular, we specify the NLI protocol architecture by introducing a corpus of NLIs, an NLI generation module, and an NLI parsing module, wherein the corpus contains control instructions, intents and slots, the generation module is used to generate NLIs, and the parsing module is used to parse the intents and slots in the instruction. Furthermore, we case-study the proposed NLI protocol in an electromagnetic interference avoidance scenario based on semi-physical simulation with software-defined radio. Simulation results show that the NLI protocol is more robust and efficient than traditional control protocol in severe wireless channels, which validates the feasibility and effectiveness of implementing intelligent machine collaboration based on NLI.

关键词：

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：