检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Zhao, Shuo Gu, Qiliang Zhang, Jianqiang Song, Gongpeng Lu, Qin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (纸本)9781665410205

Chinese short text similarity computation stands as a pivotal task within natural language processing, garnering significant attention. However, existing models grapple with limitations in handling intricate semantic relationships, such as the challenge of discerning subtle semantic nuances in text, inadequacies in effectively integrating diverse levels of semantic information, and the struggle to capture polysemous meanings accurately. In addressing these issues, this paper introduces an innovative Chinese short text similarity computation model, SMGC-SBERT. This model addresses shortcomings of the existing models by employing a multi-module fusion strategy, thereby enabling a more precise measurement of semantic similarity between texts. Primarily, the model incorporates SAT embedding to acquire phrase-level semantic information and leverages the MS-BERT model to encode text, improving the model's comprehension of textual polysemy and obtaining richer semantic representation. Then, the fusion of module features, including multi-branch convolutional networks and mix pooling, enables the extraction of textual features from varied levels, bolstering the model's representational capacity. Additionally, to further reduce overfitting risks while improving accuracy and other performance, a multi-layer feature adjustment network is utilized for short text similarity calculation. The final resultant experimental findings showcase the superiority of the SMGC-SBERT model over other neural network models, demonstrating significant advancements across both Chinese-SNLI and CCKS2018_Task3 Chinese short text datasets. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cetus: an efficient symmetric searchable encryption against file-injection attack with SGX

引用

Science China(Information Sciences) 2021年第8期64卷 195-212页

作者： Yanyu HUANG Siyi LV Zheli LIU Xiangfu SONG Jin LI Yali YUAN Changyu Dong College of Cyber Science and the College of Computer Science Tianjin Key Laboratory of Network and Data Security TechnologyNankai University School of Computer Science and Technology Shandong University School of Computer Science Guangzhou University Department of Computer Science University of G?ttingen School of Computing Newcastle University

Symmetric searchable encryption(SSE) allows the users to store and query their private data in the encrypted database. Many SSE schemes for different scenarios have been proposed in the past few years, however, most of these schemes still face more or fewer security issues. Using these security leakages,many attacks against the SSE scheme have been proposed, and especially the non-adaptive file injection attack is the most serious. Non-adaptive file injection attack(NAFA) can effectively recover some extremely important private information such as keyword plaintext. As of now, there is no scheme that can effectively defend against such attacks. We first propose the new security attribute called toward privacy to resist nonadaptive file injection attacks. We then present an efficient SSE construction called Cetus to achieve toward privacy. By setting up a buffer and designing the efficient oblivious reading algorithm based on software guard extensions(SGX), we propose the efficient one-time oblivious writing mechanism. Oblivious writing protects the update pattern and allows search operations to be performed directly on the data. The experiment results show that Cetus achieves O(aw) search time and O(1) update communication. The practical search time, communication, and computation overheads incurred by Cetus are lower than those of state-of-the-art.

关键词： searchable encryption SGX technique file injection attack forward/toward privacy cloud databases

来源：评论

学校读者我要写书评

暂无评论

Petri Net Model of MITM Attack Based on NDP Protocol

Petri Net Model of MITM Attack Based on NDP Protocol

引用

2022 International Conference on networking and network Applications, NaNA 2022

作者： Zhang, Liumei Han, Yu Wang, Yichuan Quan, Ruiqin School of Computer Science Xi’an Shiyou University Xi’an China 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 Xinjiang Institute of Engineering China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

Neighbor Discovery Protocol (NDP) is one of the core protocols of IPv6 networks. Since NDP messages are an unauthenticated stateless protocol, they are vulnerable to various types of attacks, and Man-In-The-Middle (MITM) attacks are one of the most well-known attacks in the computer field. During NDP address resolution, attackers change their own IP-MAC mapping relationships by sniffing NA (Neighbor Advertisement) messages, thus spoofing the source host's neighbor cache table and compromising the confidentiality, integrity and availability of the IPv6 network. Therefore, this paper focuses on the MITM attack in the NDP address resolution process, and performs a fine-grained analysis and Petri Net modelling of the attack process. © 2022 IEEE.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

DetecVFuzz: Enhancing security in Consumer Electronic Devices Through Scalable Vulnerability Testing of Virtual Devices

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Xiao, Xi Guo, Yongjian Jolfaei, Alireza Chen, Chuan Haghighi, Mohammad Sayad Wen, Sheng Lin, Yuanyi Tsinghua University Shenzhen International Graduate School Shenzhen China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education China Peng Cheng Laboratory Guangdong Shenzhen China Flinders University College of Science and Engineering SA5042 Australia Shandong Computer Science Center Key Laboratory of Computing Power Network and Information Security Ministry of Education China Qilu University of Technology Shandong Academy of Sciences National Supercomputer Center in Jinan Jinan China Swinburne University of Technology School of Science Computing and Engineering Technologies MelbourneVIC3122 Australia

The interconnection facilitated by consumer electronics has led to the creation of a complex network of devices. Testing efficiency of such consumer electronic devices can be improved through hardware emulation. QEMU is a classical emulator for simulation and testing. Fuzzing is a promising solution to test the security of such devices, which has become pivotal in identifying device vulnerability. However, Qtest libfuzzer, the QEMU native fuzzer, requires manual writing of stub code, which makes conducting the fuzzing process difficult and yields poor performance. To address these challenges in virtual device security analysis, we propose DetecVFuzz, a novel automatic fuzzing framework based on QEMU-Qtest, aiming to find vulnerabilities in virtual PCI devices, including USB, audio, network, etc. We inject mutated inputs into nested data structures as parameters of memory-related APIs to ensure the stable operation of VM procedures. We implemented DetecVFuzz and evaluated it on different virtual devices, such as virtual memory USB stack and drivers. In preliminary evaluations on nine recent versions of the QEMU, we found 15 new memory errors in virtual devices. In general, DetecVFuzz achieves 89.37% line coverage and 78.65% branch coverage in virtual devices. We identified 26 new crashes/errors, three of which were unseen new bugs. © 1975-2011 IEEE.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

LGDB-Net: Dual-Branch Path for Building Extraction from Remote Sensing Image 30

LGDB-Net: Dual-Branch Path for Building Extraction from Remo...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Zhang, Ronghuan Zhao, Jing Li, Ming Zou, Qingzhi Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China Shandong University of Traditional Chinese Medicine School of Intelligence and Information Engineering Jinan China

ISBN: (纸本)9798331515966

Extracting buildings from remote sensing images using deep learning techniques is a widely applied and crucial task. Convolutional Neural networks (CNNs) adopt hierarchical feature representation, showcasing powerful capabilities in extracting local information but facing challenges in capturing global features. Transformers can address this limitation, but they perform poorly in extracting local features and significantly increase memory requirements and computational complexity. To overcome these challenges, we propose a method for building extraction from remote sensing images called LGDB-Net (Local-Global Dual-Branch network), employing a dual-branch approach. Firstly, inspired by Swin Transformer, we designed GB-Former(Global Branch-Former) as the backbone network to model global information. We use a linear multi-head self-attention mechanism to reduce time and memory complexity while maintaining a large global receptive field. Additionally, we replace the traditional multi-layer perceptron with a convolution-enhanced multi-layer perceptron to improve channel feature representation, reduce model parameters, and enhance segmentation performance. Secondly, we use multiple Depth-wise Conv3×3 + LN (Layer Normalization) + GeLU (Gaussian Error Linear Unit) modules as the auxiliary branch for local detailed feature extraction. Finally, we adopt a multi-scale feature fusion strategy to integrate feature information from both branches. We conduct a series of experiments on three datasets: WHU, Massachusetts, and Inria. The experimental results demonstrate that the proposed method not only effectively improves segmentation accuracy with lower building omission and commission rates but also significantly reduces model parameters and computational complexity. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Apple Leaf Disease Detection Based on Yolov7 with Parameter-Free Attention Mechanism

SSRN

引用

SSRN 2023年

作者： Zhao, Minghua Han, Siqi Du, Shuangli Hu, Jing Lv, Zhiyong Wang, Lin Li, Peng School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an710048 China

China is an argicultural country, and apples are one of the most prominentfruits with high production volume. Apple leaf diseases are the major factors that aﬀect both the quantity and quality of apple production. Usually,complex background and small disease area in apple leaf images make it difcult to accurately detect leaf disease. In this paper, we propose an improvedYOLOv7 method, called YOLOv7-PFA (YOLOv7 with Parameter-Free Attention Mechanism) . Based on the YOLOv7 algorithm, to improve themodel’s detection ability for small targets and enhance the detection accuracy, we introduces the parameter-free attention mechanism SimAM (Simple,Parameter-Free Attention Module). To reduce the model parameters whileensuring the detection accuracy, the GSConv and VoVGSCSP (Vortex ofvectorized and cross stage partial network) modules are introduced. Lastly,to optimize the issue of sample imbalance in bounding box regression tasks,the model’s loss function is modifed to EIOU Loss to further enhance thedetection accuracy. Compared with the YOLOv7 algorithm, the YOLOv7-PFA algorithm increases Precision by 4.2%, Recall by 3.4%, and mAP by3.2%, while reducing the parameter amount by 14%. The experimental results show that the use of the YOLOv7-PFA algorithm can better solve theproblem of misjudgment and omission under complex backgrounds. © 2023, The Authors. All rights reserved.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Research on long and short-term social recommendation based on convolutional and gated recurrent units 29

Research on long and short-term social recommendation based ...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Jia, Zihe Xue, Peng Dai, Zhiqiang Gao, Qian Zhang, Xiaomeng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China

ISBN: (纸本)9798350330717

The development of the Internet has made people more closely related and has put forward higher requirements for recommendation models. Most recommendation models are studied only for the long-term interests of users. In this paper, the interaction time between the user and the item is introduced as auxiliary information in the model construction. Interaction time is used to determine users' long-term preferences and short-term preferences. In this paper, temporal features are extracted by building a convolutional gated recurrent unit with attention neural network (CNN-GRU-Attention). Firstly, for the problem of accurate feature extraction, CNN are constructed to extract higher-level and more abstract features of themselves and transform high-dimensional data into low-dimensional data;secondly, for the problem of social temporality, GRU are used to not only extract temporal information, but also effectively reduce gradient dispersion, making model convergence and training easier;finally, Graph Attention networks are used to aggregate the social relationship information of users and items respectively, which constitute the final feature representation of users and items respectively. In particular, a modified cosine similarity is used to reduce the error caused by data insensitivity when constructing the social information of the item. In this study, simulation experiments are conducted on two publicly available datasets (Epinions and Ciao), and the experimental results show that the proposed recommended model performs better than other social recommendation models, improving the evaluation metrics of MAE and RMSE by 1.06%-1.33% and 1.19%-1.37%, respectively. The effectiveness of the model innovation is proved. © 2023 IEEE.

关键词： convolutional gated recurrent unit graph attention networks neighborhood recommendation systems social networks

来源：评论

学校读者我要写书评

暂无评论

Augmentation-aware self-supervision for data-efficient GAN training 23

Augmentation-aware self-supervision for data-efficient GAN t...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Liang Hou Qi Cao Yige Yuan Songtao Zhao Chongyang Ma Siyuan Pan Pengfei Wan Zhongyuan Wang Huawei Shen Xueqi Cheng CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences and Kuaishou Technology CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences CAS Key Laboratory of AI Safety and Security Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences Kuaishou Technology CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences

Training generative adversarial networks (GANs) with limited data is challenging because the discriminator is prone to overfitting. Previously proposed differentiable augmentation demonstrates improved data efficiency of training GANs. However, the augmentation implicitly introduces undesired invariance to augmentation for the discriminator since it ignores the change of semantics in the label space caused by data transformation, which may limit the representation learning ability of the discriminator and ultimately affect the generative modeling performance of the generator. To mitigate the negative impact of invariance while inheriting the benefits of data augmentation, we propose a novel augmentation-aware self-supervised discriminator that predicts the augmentation parameter of the augmented data. Particularly, the prediction targets of real data and generated data are required to be distinguished since they are different during training. We further encourage the generator to adversarially learn from the self-supervised discriminator by generating augmentation-predictable real and not fake data. This formulation connects the learning objective of the generator and the arithmetic - harmonic mean divergence under certain assumptions. We compare our method with state-of-the-art (SOTA) methods using the class-conditional BigGAN and unconditional StyleGAN2 architectures on data-limited CIFAR-10, CIFAR-100, FFHQ, LSUN-Cat, and five low-shot datasets. Experimental results demonstrate significant improvements of our method over SOTA methods in training data-efficient GANs. Our code is available at https://***/liang-hou/augself-gan.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Trusted Privacy-Preserving Model for Cross-Chain Transactions Based on zk_SNARKs

A Trusted Privacy-Preserving Model for Cross-Chain Transacti...

引用

International Conference on networking and network Applications (NaNA)

作者： Yichuan Wang Jianhuan Tie Xinhong Hei Li Zhao Xiaohui Zhang School of Computer Science and Engineering Xi'an University of Technology Xi'an China Shaanxi Key Laboratory for Network Computing and Security Technolog Xi'an China

Currently, the privacy protection technology of blockchain is not mature enough, such as user data leakage and lack of anonymity exist, and these problems are especially serious when conducting cross-chain transactions. In this paper, we propose a method of cross-chain transactions based on zk_SNARKs in a trusted environment for cross-chain transactions for privacy protection. Cross-chain transactions are performed through the features of zk_SNARKs such as efficiency, privacy, and verifiability. zk_SNARKs needs to generate trusted settings with the help of a third party during the transaction, and the process has serious privacy issues, and the private parameters generated during the transaction may be maliciously attacked and thus obtained by attackers. To address this problem, we use a hardware technology SGX for trusted computing to encrypt and store some private parameters generated by zk_SNARKs, thus ensuring the security of cross-chain transactions. The experimental results show that the privacy protection scheme using SGX for cross-chain transactions takes less time than the traditional transaction privacy protection, with a verification time of 1.2s for a number of 10 sidechains, and is more efficient than the traditional cross-chain transaction privacy protection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Malicious Client Detection with Differential Privacy Constraints Based on Model Update Slicing and K-Means Clustering

Malicious Client Detection with Differential Privacy Constra...

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Mengshi Qi Xin Wang Yunpeng He Ming Yang Xiaoming Wu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Federated learning (FL) is a decentralized machine learning technique that protects data privacy by trainng models locally on devices and sharing only model updates instead of raw data. However, FL also faces multiple security challenges. Clientside poisoning attacks can compromise global model training by injecting malicious updates. Additionally, the server may infer private information from client model updates. Most existing studies address these two risks separately, lacking a systematic analysis and response to their combined threats. This paper proposes a method called Sliced-Clustering Guard (SCGuard), which slices gradients and performs clustering analysis on each segment, enabling the server to more accurately detect malicious updates and effectively differentiate malicious client updates with differential privacy (DP) protection. Experimental results demonstrate that SCGuard can mitigate poisoning attacks while effectively safeguarding clients' sensitive information.

关键词： Training Privacy Differential privacy Systematics Federated learning Scalability Data models Servers Protection Faces

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：