检索结果-内蒙古大学图书馆

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Ming Lang Wang Yongli Huang Yuanyuan Chen Junyu School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology Chengdu China Dazhou key Laboratory of Government data security Dazhou China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

Face images contain rich and sensitive personal information. Direct release of facial images on the Internet may lead to the disclosure of personal information. In order to protect the privacy information in facial images, this paper proposes a PMP method based on neighboring pixels merging, which meets the requirements of differential privacy. First, the gray scale matrix of the face image is leveled into a one-dimensional data stream and the position index of each pixel is recorded while traverse through the pixels. Given the large number of duplicate pixels in the face image, duplicate pixels as well as neighboring pixels were grouped to reduce the sensitivity of differential privacy, and noise was subsequently added to each group. Eventually, each pixel is replaced to its original position according to the index, and the new one-dimensional data stream is converted back to the original matrix structure. The experiment based on real face image data set used the combination of support vector machine (SVM) and principal component analysis (PCA). The results show that the PMP algorithm is 30.57% higher than the LAP algorithm in terms of the average accuracy of face recognition, and the proposed PMP algorithm has higher usability and robustness.

关键词： Support vector machines Differential privacy Privacy Sensitivity Publishing Face recognition Noise Streaming media Protection Matrix converters

来源：评论

学校读者我要写书评

暂无评论

A Blockchain-Based Risk Assessment Model for Heterogeneous Identity Alliance 8th

A Blockchain-Based Risk Assessment Model for Heterogeneous I...

引用

8th International Conference on Artificial Intelligence and security , ICAIS 2022

作者： Yang, Yanbo Wan, Wunan Zhang, Shibin Zhang, Jinquan Qin, Zhi Xia, Jinyue School of Cybersecurity Chengdu University of Information Technology Chengdu610225 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610255 China New York10041 NY 212 United States

ISBN: (纸本)9783031067631

Heterogeneous identity alliance technology solves the identity management problem under heterogeneous networks by building a unified and trusted identity management system, while the risk assessment system of heterogeneous identity alliance can analyze potential security problems in heterogeneous identity alliance in advance, so as to realize timely supervision and maintenance of identity when crossing domains and reduce the proliferation of security problems. A blockchain-based risk assessment model for heterogeneous identity alliance is proposed for existing risk assessment systems that are generally centralized architectures with single point of failure, internal mischief, and loss of control of user data. The model uses attribute encryption to guarantee the secure storage of privacy data, while ensuring that the control of risk assessment-related data is always in the hands of the data owner, and simplifies the three-stage PBFT (Practical Byzantine Fault Tolerance) consensus to two stages to improve the efficiency of risk assessment result processing. Finally, a comparison experiment shows that compared to the three-stage PBFT, the two-stage PBFT reduces the number of communications to reach consensus and improves the throughput by about 7%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

An Embedding-Based Multi-Modal Few-Shot Learning Method for Network Intrusion Detection

An Embedding-Based Multi-Modal Few-Shot Learning Method for ...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： He Qiulin Zhang Jinquan Huang Yuanyuan School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu China Dazhou key Laboratory of Government data security Dazhou China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

In this paper, we introduce an embedding-based few-shot learning framework, aiming to achieve classification by calculating the similarity measure between unknown samples and known samples in the embedding space. This framework mainly consists of two parts: embedding space and similarity calculation stage. In the embedding space, semantic information and visual features are embedded into a common space to achieve multi-modal embedding. In the similarity calculation stage, the classification task is achieved by calculating multiple score indicators between vectors. The experimental results show that when the number of support sets is 5, the accuracy on the CICIDS2017 and KDDCUP99 datasets reaches 98.89% and 99.85%, demonstrating excellent performance in the domain of few-shot learning for intrusion detection.

关键词： Training Learning systems Visualization Accuracy Semantics Network intrusion detection Information processing Media Vectors Few shot learning

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Fusion Model for Android Malware Detection Leveraging Multi-Code Fragment Features and Fuzzy Hashing

An Enhanced Fusion Model for Android Malware Detection Lever...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Han Lingrong Zhang Shibin Lu Jiazhong Huang Yuanyuan Qin Zhi School of Cybersecurity Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu China

Traditional methods for detecting Android malware require large-scale datasets and complex feature engineering, which are unable to adapt to complex malicious features. Additionally, feature engineering based on fuzzy hash algorithms is w idely used but susceptible to bypass attacks by adversaries. To address these issues, this paper proposes an Android malware detection model that multiple Android code snippet features with fuzzy hash features. Simulation experiments demonstrate that using fused fuzzy hash features improves the accuracy of Android malware detection by 7.03%, precision by 6.23%, recall by 13.78%, and F1 score by 9.88% compared to using single fuzzy hash features. The proposed detection method not only focuses on partial features of function call sequences and behaviors of malicious applications but also considers the correlation between call sequences and behaviors, enabling it to adapt to more complex Android malware detection scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Side-Channel Analysis and Countermeasures of Domestic Block Cipher uBlock

Side-Channel Analysis and Countermeasures of Domestic Block ...

引用

International Conference on Information, Communication and Networks (ICICN)

作者： Xinyan Shang Kaifeng Liang Congming Wei Yaoling Ding Shaofei Sun An Wang School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Key Laboratory of Cryptography of Zhejiang Province Hangzhou Normal University Hangzhou China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Sichuan China

Nowadays, IoT devices are ubiquitous. Addressing data security issues in resource-limited devices is a key focus of IoT security. Therefore, lightweight cryptographic algorithms and their security research have received increasing attention. The uBlock is a lightweight block cipher proposed in 2019, which has advantages in software performance and hardware implementation, such as efficiency and low energy consumption. Research shows that the uBlock can effectively resist traditional analysis methods such as integral analysis and differential analysis. However, there is currently a lack of related research showing that the uBlock can effectively resist side-channel analysis. In this paper, we successfully complete the correlation power analysis on the uBlock and give specific experimental results. Subsequently, we propose a masking countermeasure for the uBlock software implementation and prove its security against correlation power analysis. Its implementation shows that the protected uBlock has increased code size, time, and RAM consumption by 37.73%, 38.31%, and 20.80%, respectively, compared to the unprotected one.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum Fuzzy Least Squares Algorithm for Uncertain Environment 8th

Quantum Fuzzy Least Squares Algorithm for Uncertain Environm...

引用

8th International Conference on Artificial Intelligence and security , ICAIS 2022

作者： Yu, Shipeng Chang, Yan Zhang, Shibin Wang, Qirun School of Cybersecurity Chengdu University of Information Technology Chengdu610225 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610255 China School of Engineering and Technology University of Hertfordshire Hertford United Kingdom

ISBN: (纸本)9783031067662

With the development of information technology, modern society has entered the era of big data. Big data means a huge amount of data, as well as the complexity and uncertainty of data. In order to find valuable data efficiently and accurately from the big data environment, researchers use machine learning algorithms to establish relevant data models to predict and classify new data. In the process of establishing the linear system model, the commonly used method is the least square method, which can easily obtain the optimal parameters of the linear system and make the established linear model more accurate. In order to deal with the fuzziness of the data itself and reduce the influence of abnormal data on the linear model, researchers put forward the fuzzy linear model. When the amount of data is increasing, the time required for traditional computers to process data and establish models is increasing. In order to reduce the time of establishing the model, a quantum fuzzy least square method is proposed on the basis of predecessors. The algorithm uses the advantages of quantum computing in data processing to improve the efficiency of fuzzy linear model establishment and reduce the model establishment time. Relevant research and analysis prove the efficiency of the algorithm. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Spiderweb Protector: Biomimetic Defense Against Targeted Attacks on Graph Neural Networks

Spiderweb Protector: Biomimetic Defense Against Targeted Att...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Zeyu Zhou Yuanyuan Huang Yongli Wang Siyu Li Jiazhong Lu Peilin He Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu University of Information Technology Chengdu China Dazhou key Laboratory of Government data security Dazhou China Department of Informatics and Networked Systems University of Pittsburgh Pittsburgh United States

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

Graph Neural Networks (GNNs) have emerged as powerful tools across diverse applications, including social networks, bioinformatics, and recommendation systems. However, their susceptibility to adversarial attacks, particularly targeted attacks, poses a significant challenge. Targeted attacks exploit the message-passing mechanism of GNNs to induce severe performance degradation, even with minimal perturbations. Inspired by the self-repair and adaptive behaviors of spider webs, this paper introduces SpiderWeb Protector, a biomimetic defense strategy designed to enhance GNN robustness. The proposed method integrates three core components: Community-Centric Graph Update, which selectively reinforces key graph structures; Topology Feature Merging, which improves feature representation by incorporating structural insights; and Edge Pruning, which dynamically removes adversarial connections. Comprehensive experiments on three datasets (Cora, Citeseer and Cora_ml) and two GNN models (GCN and GIN) demonstrate the superior performance of SpiderWeb Protector against both direct and influence-targeted attacks, achieving state-of-the-art results.

关键词： Technological innovation Social networking (online) Biomimetics Merging Refining Graph neural networks Robustness Topology Recommender systems Resilience

来源：评论

学校读者我要写书评

暂无评论

Enhanced Lightweight Network with CNN and Improved Transformer for Image Super-Resolution

Enhanced Lightweight Network with CNN and Improved Transform...

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Hengyu Li Juan Wang Jie Liu Ding Chen Lei Shi Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu University of Information Technology Chengdu China

In recent years, there have been significant advancements in deep learning-based lightweight image super-resolution (SR) reconstruction techniques. However, in practical applications, there are still challenges to be addressed. Many existing lightweight SR reconstruction algorithms simplify the model by reducing the number of model parameters or changing the combination of convolutions, which results in significantly decreased model performance and stability, leading to poor reconstruction results. To address this issue, we proposed a Cosine Self-Attention mechanism and deepens the network depth to improve the Swin Transformer, enhanced the model’s performance and stability. Experimental results show that the proposed approach achieves stronger and more stable reconstruction performance with lower parameter count than existing lightweight SR models, outperforming them in reconstruction results and model complexity. The PSNR/SSIM of our proposed method for ×2 and ×4 SR reconstruction on the Set5, Set14, BSD100, Urban100, and Manga109 datasets exceed those of most existing lightweight SR models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Effective Segment Extraction of Ship Surveillance Videos

Research on Effective Segment Extraction of Ship Surveillanc...

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Jie Liu Juan Wang Hengyu Li Ding Chen Lei Shi Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu University of Information Technology Chengdu China

Effective segment extraction has broad application prospects in the field of video surveillance. In action recognition or object recognition, a large number of repetitive background segments will reduce the efficiency of computation. This causes the algorithm to consume more time. Effective segments can greatly save computing and storage resources for both target detection and storage. Common algorithms are to process the whole surveillance video, such as frame difference method and optical flow method. However, false detection can occur when the picture is disturbed, such as snowflakes. Will result in low accuracy. The effective segment detection method adopted in this paper. First convert the color space. The surveillance video is then segmented. Features were extracted and repeated segments filtering was carried out to reduce the interference of bad images. Finally, effective segments are extracted. Experimental results show that the accuracy of the effective segment detection method adopted in this paper is increased by more than 50%, and the F-metric value is increased by more than 24%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum Remote State Preparation Based on Quantum Network Coding

引用

Computers, Materials & Continua 2022年第10期73卷 119-132页

作者： Zhen-Zhen Li Zi-Chen Li Yi-Ru Sun Haseeb Ahmad Gang Xu Xiu-Bo Chen School of Information Engineering Beijing Institute of Graphic CommunicationBeijing102600China School of Computer Science and Information Engineering Zhejiang Gongshang UniversityHangzhou310018China Information Security Center State key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing100876China Department of Computer Science National Textile UniversityFaisalabad37610Pakistan School of Information Science and Technology North China University of TechnologyBeijing100144China Advanced Cryptography and System Security Key Laboratory of Sichuan Province China

As an innovative theory and technology,quantum network coding has become the research hotspot in quantum network *** this paper,a quantum remote state preparation scheme based on quantum network coding is *** with the general quantum remote state preparation schemes,our proposed scheme brings an arbitrary unknown quantum state finally prepared remotely through the quantum network,by designing the appropriate encoding and decoding steps for quantum network *** is worth mentioning,from the network model,this scheme is built on the quantum k-pair network which is the expansion of the typical bottleneck network—butterfly ***,it can be treated as an efficient quantum network preparation scheme due to the characteristics of network coding,and it also makes the proposed scheme more applicable to the large-scale quantum *** addition,the fact of an arbitrary unknown quantum state remotely prepared means that the senders do not need to know the desired quantum ***,the security of the proposed scheme is ***,this scheme can always achieve the success probability of 1 and 1-max flow of value ***,the communication efficiency of the proposed scheme is ***,the proposed scheme turns out to be practicable,secure and efficient,which helps to effectively enrich the theory of quantum remote state preparation.

关键词： Quantum remote state preparation quantum network coding quantum k-pair network

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：