检索结果-内蒙古大学图书馆

A Fast Two-Stage Black-Box Deep Learning Network Attacking Method Based on Cross-Correlation

Computers, Materials & Continua 2020年第7期64卷 623-635页

作者： Deyin Li Mingzhi Cheng Yu Yang Min Lei Linfeng Shen State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China College of New Media Beijing Institute of Graphic CommunicationBeijing102600China School of Computing Science Simon Fraser UniversityBurnabyCanada

Deep learning networks are widely used in various systems that require ***,deep learning networks are vulnerable to adversarial *** study on adversarial attacks plays an important role in ***-box attacks require less knowledge about target models than white-box attacks do,which means black-box attacks are easier to launch and more ***,the state-of-arts black-box attacks still suffer in low success rates and large visual distances between generative adversarial images and original *** paper proposes a kind of fast black-box attack based on the cross-correlation(FBACC)*** attack is carried out in two *** the first stage,an adversarial image,which would be missclassified as the target label,is generated by using gradient descending *** far the image may look a lot different than the original ***,in the second stage,visual quality keeps getting improved on the condition that the label keeps being *** using the cross-correlation method,the error of the smooth region is ignored,and the number of iterations is *** with the proposed black-box adversarial attack methods,FBACC achieves a better fooling rate and fewer *** attacking LeNet5 and AlexNet respectively,the fooling rates are 100%and 89.56%.When attacking them at the same time,the fooling rate is 69.78%.FBACC method also provides a new adversarial attack method for the study of defense against adversarial attacks.

关键词： Black-box adversarial attack cross-correlation two-module

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection Algorithm for the Internet of Vehicles Based on Local Differential Privacy and Game Model

引用

Computers, Materials & Continua 2020年第8期64卷 1025-1038页

作者： Wenxi Han Mingzhi Cheng Min Lei Hanwen Xu Yu Yang Lei Qian Guizhou Provincial Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing100876China College of New Media Beijing Institute of Graphic CommunicationBeijing102600China School of Computer Science The University of AucklandAucklandNew Zealand

In recent years,with the continuous advancement of the intelligent process of the Internet of Vehicles(IoV),the problem of privacy leakage in IoV has become increasingly *** research on the privacy protection of the IoV has become the focus of the *** paper analyzes the advantages and disadvantages of the existing location privacy protection system structure and algorithms,proposes a privacy protection system structure based on untrusted data collection server,and designs a vehicle location acquisition algorithm based on a local differential privacy and game *** algorithm first meshes the road network ***,the dynamic game model is introduced into the game user location privacy protection model and the attacker location semantic inference model,thereby minimizing the possibility of exposing the regional semantic privacy of the k-location set while maximizing the availability of the *** this basis,a statistical method is designed,which satisfies the local differential privacy of k-location sets and obtains unbiased estimation of traffic density in different ***,this paper verifies the algorithm based on the data set of mobile vehicles in *** experimental results show that the algorithm can guarantee the user’s location privacy and location semantic privacy while satisfying the service quality requirements,and provide better privacy protection and service for the users of the IoV.

关键词： The Internet of Vehicles privacy protection local differential privacy location semantic inference attack game theory

来源：评论

学校读者我要写书评

暂无评论

Ads-Cnn: Adaptive dataflow Scheduling for Lightweight Cnn Accelerator on Fpgas

SSRN

引用

SSRN 2023年

作者： Wan, Yi Xie, Xianzhong Chen, Junfan Xie, Kunpeng Yi, Dezhi Lu, Ye Gai, Keke The College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Haiyunjiexun Technology Co. Ltd Chongqing China The College of Computer Science Nankai University Tianjin300350 China The College of Cyber Science Nankai University Tianjin300350 China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China State Key Laboratory of Processors ICT CAS Beijing China School of Cyberspace Science and Technology BIT Beijing China

Lightweight convolutional neural networks (CNNs) enable lower inference latency and data traffic, which are suitable for deployment on resource-constrained edge devices such as field-programmable gate arrays (FPGAs). However, repeated data access to off-chip synchronous dynamic random-access memory (SDRAM) is required during inference, which seriously results in a reduction in inference speed and system power efficiency. In this paper, we propose an adaptive dataflow scheduling method for lightweight CNN accelerator on FPGAs named ADS-CNN. The key idea of ADS-CNN is to efficiently utilize on-chip resources and reduce the amount of SDRAM access. To achieve the reuse of logical resources, we designed a time division multiplexing calculation engine in ADS-CNN. We developed a configurable module for the convolution controller, and the adaptability is reflected in the data reuse of different convolution layers, which reduces the off-chip access. Furthermore, we made rational use of on-chip memory blocks as buffers based on the configuration of different layers in lightweight CNNs. On the resource-constrained Intel CycloneV SoC 5CSEBA6 FPGA platform, we evaluated six common lightweight CNN models to demonstrate the performance advantages of ADS-CNN. The evaluation results indicate that, compared with accelerators using traditional tiling strategy dataflow, our ADS-CNN can achieve up to 1.29× acceleration gains with a 23.7% overall dataflow scale compression. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PSSPR: A source location privacy protection scheme based on sector phantom routing in WSNs

arXiv

引用

arXiv 2021年

作者： Chen, Yuling Sun, Jing Yang, Yixian Li, Tao Niu, Xinxin Zhou, Huiyu State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Cyberspace Security Beijing University of Posts and Telecommnuications Beijing China School of Informatics University of Leicester England United Kingdom Guangxi Key Laboratory of Cryptography and Information Security

Source location privacy (SLP) protection is an emerging research topic in wireless sensor networks(WSNs). Because the source location represents the valuable information of the target being monitored and tracked, it is of great practical significance to achieve a high degree of privacy of the source location. Although many studies based on phantom nodes have alleviates the protection of source location privacy to some extent. It is urgent to solve the problems such as complicate the ac path between nodes, improve the centralized distribution of Phantom nodes near the source nodes and reduce the network communication overhead. In this paper, PSSPR routing is proposed as a visable approach to address SLP issues. We use the coordinates of the center node V to divide sector-domain, which act as important role in generating a new phantom nodes. The phantom nodes perform specified routing policies to ensure that they can choose various locations. In addition, the directed random route can ensure that data packets avoid the visible range when they move to the sink node hop by hop. Thus, the source location is protected. Theoretical analysis and simulation experiments show that this protocol achieves higher security of source node location with less communication overhead. Copyright © 2021, The Authors. All rights reserved.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

Vulnerability Detection With Graph Attention Network And Metric Learning

TechRxiv

引用

TechRxiv 2022年

作者： Zhang, Chunyong Liu, Bin Fan, Qi Xin, Yang Zhu, Hongliang School of Cyberspace Security Beijing University of Posts and Telecommunications Beijing100876 China College of Information and Network Engineering Anhui Science and Technology University Bengbu233030 China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

Static code vulnerability detection is a critical topic in software security. Existing software analysis methods have a high rate of false positives and false negatives. Researchers are interested in employing deep learning to discover vulnerabilities automatically, thanks to the recent success of deep learning algorithms in other application *** paper aims at the problem of insufficient and effective extraction of syntax and semantics, the issue of data imbalance, and the problem of overlapping feature distributions between vulnerable and non-vulnerable samples. We illustrate how to create models in a more principled way. We build GSM, a systematic vulnerability detection model based on Graph Attention Network, Sampling methods, and Metric Learning, one phase for one problem solution. When compared to the state-of-the-art approaches, our method achieves 11.5%, 12.3%, 12.57%, and 7.90% improvement in Precision, Recall, F1-Score, and AUC, respectively. Finally, based on the methods proposed in each stage of this paper, we put forward directions and suggestions for more efficient vulnerability detection tasks in the following research. © 2022, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Inductive Subgraph Embedding for Link Prediction

arXiv

引用

arXiv 2021年

作者： Miao, Chunyu Xie, Chenxuan Zhou, Jiajun Yu, Shanqing Chen, Lina Xuan, Qi The College of Mathematics Physics and Information Engineering Zhejiang Normal University Zhejiang Jinhua310023 China The Key Laboratory of Peace-building Big Data of Zhejiang Province Hangzhou310051 China The Institute of Cyberspace Security Zhejiang University of Technology Hangzhou310023 China The Binjiang Cyberspace Security Institute of ZJUT Hangzhou310023 China

Link prediction, which aims to infer missing edges or predict future edges based on currently observed graph connections, has emerged as a powerful technique for diverse applications such as recommendation, relation completion, etc. While there is rich literature on link prediction based on node representation learning, direct link embedding is relatively less studied and less understood. One common practice in previous work characterizes a link by manipulate the embeddings of its incident node pairs, which is not capable of capturing effective link features. Moreover, common link prediction methods such as random walks and graph auto-encoder usually rely on full-graph training, suffering from poor scalability and high resource consumption on large-scale graphs. In this paper, we propose Inductive Subgraph Embedding for Link Prediciton (SE4LP) - an end-to-end scalable representation learning framework for link prediction, which utilizes the strong correlation between central links and their neighborhood subgraphs to characterize links. We sample the "link-centric induced subgraphs" as input, with a subgraph-level contrastive discrimination as pretext task, to learn the intrinsic and structural link features via subgraph classification. Extensive experiments on five datasets demonstrate that SE4LP has significant superiority in link prediction in terms of performance and scalability, when compared with state-of-the-art methods. Moreover, further analysis demonstrate that introducing self-supervision in link prediction can significantly reduce the dependence on training data and improve the generalization and scalability of model. The source code will be available online. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Preface

引用

Science China Technological Sciences 2024年

作者： Gong YiHong Wang GuoYin College of Artificial Intelligence Xi'an Jiaotong University Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications College of Computer and Information Science Chongqing Normal University

Large AGI(artificial general intelligence) models, represented by OpenAI's GPT-4, DALL-E, Sora, etc., have amazed the world by exhibiting superior capabilities on a variety of NLP and text-to-image/video generation tasks. The success of these models was achieved by exploiting ultra-scale training data, ultra-scale computational models, and unlimited computing power.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Link prediction for attribute and structure learning based on attention mechanism

引用

Applied Soft Computing 2025年 179卷

作者： Renjuan Nie Guoyin Wang Qun Liu Chengxin Peng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing 400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing 400065 China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing 401331 China

The link prediction problem within complex network analysis focus on accurately inferring future relationships between unconnected node pairs in networks. In real-world scenarios, many relationships can find effective expression through network representation learning, making link prediction pivotal in solving various practical problems. However, existing link prediction methods often exhibit an over-reliance on network structure information or struggle to effectively integrate network structure with node attribute information. Moreover, the current limitations of GPU memory pose challenges for deploying graph neural network (GNN) methods at scale. To address these challenges, this paper introduces attribute and structure learning based on attention mechanism(ASLAM), a novel link prediction framework that amalgamates graph neural networks with attention mechanisms. ASLAM adeptly extracts and integrates both node attribute and structural information, constructing semantic and structural node representations through attention mechanisms and facilitating predictions via adaptive merging. Additionally, to mitigate GPU memory consumption, ASLAM innovatively incorporates the subgraph history embedding method, ensuring stable performance with either constant or linear increases in memory consumption. Experimental results show ASLAM’s superiority over baseline methods across nine real datasets in link prediction tasks. The AUC and AP metrics witness enhancements ranging from 0.11% to 3.03% and 0.15% to 3.32%, respectively, underscoring its promise and applicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Algorithms Design and Implementation Based on Differential Privacy 3rd

Deep Learning Algorithms Design and Implementation Based on ...

引用

3rd International Conference on Machine Learning for Cyber security, ML4CS 2020

作者： Xu, Xuefeng Yao, Yanqing Cheng, Lei Key Laboratory of Aerospace Network Security Ministry of industry and information technology School of Cyberspace Science and Technology Beihang University Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Beijing Key Laboratory of Network Technology Beihang University Beijing China Shenzhen Research Institute of Big Data Shenzhen518000 China

ISBN: (纸本)9783030622220

Deep learning models bear the risks of privacy leakage. Attackers can obtain sensitive information contained in training data with some techniques. However, existing differentially private methods such as Differential Privacy-Stochastic Gradient Descent (DP-SGD) and Differential Privacy-Generative Adversarial Network (DP-GAN) are not very efficient as they require to perform sampling multiple times. More importantly, DP-GAN algorithm need public data to set gradient clipping threshold. In this paper, we introduce our refined algorithms to tackle these problems. First, we employ random shuffling instead of random sampling to improve training efficiency. We also test Gaussian and Laplace Mechanisms for clipping gradients and injecting noise. Second, we employ zero Concentrated Differential Privacy (zCDP) to compute overall privacy budget. Finally, we adopt dynamical gradient clipping in DP-GAN algorithm. During each iteration, we random sample training examples and set the average gradients norm as the new threshold. This not only makes the algorithm more robust but also doesn’t increase the overall privacy budget. We experiment with our algorithms on MNIST data sets and demonstrate the accuracies. In our refined DP-SGD algorithm, we achieve test accuracy of 96.58%. In our refined DP-GAN algorithm, we adopt the synthetic data to train models and reach test accuracy of 91.64%. The results show that our approach ensures model usability and provides the capability of privacy protection. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

PSSPR: A Source Location Privacy Protection Scheme Based on Sector Phantom Routing in WSNs

PSSPR: A Source Location Privacy Protection Scheme Based on ...

引用

IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC)

作者： Jing Sun Yuling Chen Tao Li Jia Liu Yixian Yang State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China Air Force Engineering University Xi'an China School of Cyberspace Security Beijing University of Posts and Telecommnuications Beijing China

ISBN: (纸本)9781665421751

Source location privacy, occupying an unshakable status in wireless sensor networks, has a profound influence on the widespread application of wireless sensor networks (WSNs). Most privacy policies that introduce phantom nodes to the source location have the problem that the transmission path between the phantom node and the source is not diversified enough, and the phantom node area is close to the source. For this reason, a source location privacy protection scheme based on sector domain phantom routing is proposed. The scheme uses the sector domain and the coordinates of the central node $V$ to increase the geographical position diversity of the phantom node, which completely avoids the visible and protects the security of the source location. Theoretical analysis and simulation results show that our scheme can enhance the security of source position.

关键词： Wireless communication Wireless sensor networks Privacy Simulation Phantoms Position measurement Routing

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：