检索结果-内蒙古大学图书馆

Face Anti-Spoofing with Unknown Attacks:A Comprehensive Feature Extraction and Representation Perspective

Journal of Computer Science & technology 2024年第4期39卷 827-840页

作者： Li-Min Li Bin-Wu Wang Xu Wang Peng-Kun Wang Yu-Dong Zhang Yang Wang School of Software Engineering University of Science and Technology of ChinaHefei 230000China School of Data Science University of Science and Technology of ChinaHefei 23000China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215000China

Face anti-spoofing aims at detecting whether the input is a real photo of a user(living)or a fake(spoofing)*** new types of attacks keep emerging,the detection of unknown attacks,known as Zero-Shot Face Anti-Spoofing(ZSFA),has become increasingly important in both academia and *** ZSFA methods mainly focus on extracting discriminative features between spoofing and living ***,the nature of the spoofing faces is to trick anti-spoofing systems by mimicking the livings,therefore the deceptive features between the known attacks and the livings,which have been ignored by existing ZSFA methods,are essential to comprehensively represent the ***,existing ZSFA models are incapable of learning the complete representations of living faces and thus fall short of effectively detecting newly emerged *** tackle this problem,we propose an innovative method that effectively captures both the deceptive and discriminative features distinguishing between genuine and spoofing *** method consists of two main components:a two-against-all training strategy and a semantic *** two-against-all training strategy is employed to separate deceptive and discriminative *** address the subsequent invalidation issue of categorical functions and the dominance disequilibrium issue among different dimensions of features after importing deceptive features,we introduce a modified semantic *** autoencoder is designed to map all extracted features to a semantic space,thereby achieving a balance in the dominance of each feature *** combine our method with the feature extraction model ResNet50,and experimental results show that the trained ResNet50 model simultaneously achieves a feasible detection of unknown attacks and comparably accurate detection of known *** results confirm the superiority and effectiveness of our proposed method in identifying the living with the interference of both known

关键词： face anti-spoofing spoof detection zero-shot learning convolutional neural network deep learning

来源：评论

学校读者我要写书评

暂无评论

SFC placement and dynamic resource allocation based on VNF performance-resource function and service requirement in cloud-edge environment

引用

Journal of Systems engineering and Electronics 2024年第4期35卷 906-921页

作者： HAN Yingchao MENG Weixiao FAN Wentao School of Electronics and Information Engineering Harbin Institute of TechnologyHarbin 150001China China Mobile(Suzhou)Software Technology Company Limited Suzhou 215000China

With the continuous development of network func-tions virtualization(NFV)and software-defined networking(SDN)technologies and the explosive growth of network traffic,the requirement for computing resources in the network has risen *** to the high cost of edge computing resources,coordinating the cloud and edge computing resources to improve the utilization efficiency of edge computing resources is still a considerable *** this paper,we focus on optimiz-ing the placement of network services in cloud-edge environ-ments to maximize the *** is first proved that,in cloud-edge environments,placing one service function chain(SFC)integrally in the cloud or at the edge can improve the utilization efficiency of edge *** a virtual network function(VNF)performance-resource(P-R)function is proposed to repre-sent the relationship between the VNF instance computing per-formance and the allocated computing *** select the SFCs that are most suitable to deploy at the edge,a VNF place-ment and resource allocation model is built to configure each VNF with its particular P-R ***,a heuristic recur-sive algorithm is designed called the recursive algorithm for max edge throughput(RMET)to solve the *** simula-tions on two scenarios,it is verified that RMET can improve the utilization efficiency of edge computing resources.

关键词： cloud-edge environment virtual network function(VNF)performance-resource(P-R)function edge resource allo-cation

来源：评论

学校读者我要写书评

暂无评论

WasmChecker: Effectively Detecting WebAssembly Bugs via Static Program Analysis 8

WasmChecker: Effectively Detecting WebAssembly Bugs via Stat...

引用

8th International Conference on Electrical, Mechanical and Computer engineering, ICEMCE 2024

作者： Zhuang, Junjie Jiang, Hao Hua, Baojian University of Science and Technology of China Suzhou Institute for Advanced Research School of Software Engineering Suzhou China

ISBN: (纸本)9798331506230

WebAssembly, a new binary instruction set, has rapidly gained popularity across fields such as blockchain, edge computing, and cloud computing due to its efficiency, security, and portability. However, recent research has identified limitations in WebAssembly's type system and linear memory design, leading to security issues such as integer overflows and memory safety *** this paper, we present WasmChecker, the first static analysis approach for WebAssembly programs based on abstract interpretation. WasmChecker consists of three components: a frontend module for parsing and constructing control flow graphs, a static analysis module for iterative state analysis, and a vulnerability filtering module to identify security flaws. We design and implement a software prototype and conduct extensive evaluations. Experiments demonstrate WasmChecker's effectiveness, achieving a 97.33% recall in a small dataset and accurately identifying 46 vulnerabilities across four real-world datasets, with a 92% recall rate. Additionally, WasmChecker shows high efficiency, with an average runtime of 13.85 seconds on WebAssembly programs smaller than 1 MB. © 2024 IEEE.

关键词： component Intermediate Representation Static Analysis Vulnerabilities Detection WebAssembly

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study of Bugs in Embedded WebAssembly Virtual Machines 3

A Comprehensive Study of Bugs in Embedded WebAssembly Virtua...

引用

3rd International Conference on Computer Science, Electronic Information engineering and Intelligent Control technology, CEI 2023

作者： Zheng, Wenlong Hua, Baojian School of Software Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China

ISBN: (纸本)9798350372052

WebAssembly is an emerging secure instruction set architecture widely used in embedded applications. Despite its success, bugs in WebAssembly virtual machines can compromise safety. This paper presents the first empirical study of bugs in embedded WebAssembly virtual machines, examining four popular ones: Wasmer, Wasmtime, WAMR, and Wasm3. We qualitatively identify unique bugs, analyze their roots, fixes, and reproductions, and conduct a quantitative study on bug lifecycles, testing, and fixing. Key findings include a proposed bug taxonomy and significant variations in bug fixing times (16.72 to 98.24 days). We recommend a dual-focus approach for developers, addressing common issues and feature-specific challenges. Our insights aim to guide WebAssembly development, testing, and tool-building for improved system quality. © 2023 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

SAFEJ: An Efficient Infrastructure for Securing Julia Programs 4

SAFEJ: An Efficient Infrastructure for Securing Julia Progra...

引用

4th International Conference on Big Data and Artificial Intelligence and software engineering, ICBASE 2023

作者： Zhu, Hao Hua, Baojian Suzhou Institute for Advanced Research University of Science and Technology of China School of Software Engineering Suzhou China

ISBN: (纸本)9798350329490

Julia is an emerging programming language designed for high-performance and parallel computing. However, its simple-designed foreign function interface, ccall, lacks necessary security checks, making multilingual Julia applications vulnerable to exploitation. This paper introduces SAFEJ, an infrastructure developed to enhance Julia FFI security. SAFEJ includes two key components: 1) privilege separation to protect Julia by isolating the memory of Julia and native code and 2) pointer sanitization to filter and check memory accesses from unsafe native code to provide more flexible protection. We conducted extensive experiments to evaluate the effectiveness and performance of SAFEJ. The results demonstrate that SAFEJ effectively protects Julia from common memory attacks, and its efficiency tests indicate that pointer sanitization is on par with prior studies, while privilege separation achieves a maximum reduction of 85% in runtime performance overhead. © 2023 IEEE.

关键词： Codes (symbols)

来源：评论

学校读者我要写书评

暂无评论

LumChromNet: A Dual-Path Neural Network Framework for Optical Measurement in VR Systems

LumChromNet: A Dual-Path Neural Network Framework for Optica...

引用

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

作者： Leng, Zhaoqing Zhao, Zhengang Yu, Yanwei Zhou, Xiaoyu Dong, Xu Zhang, Yican School of Software Engineering University of Science and Technology of China Suzhou215123 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China

ISBN: (纸本)9781665410205

Traditional optical instruments for VR glasses are costly, bulky, and complex, while current automated solutions lack sufficient measurement range and accuracy. To optimize VR glasses' optical characteristics, we introduce LumChrom-Net, an innovative dual-path neural network framework for automated production solutions. LumChromNet comprises two key components: First, for luminance calibration, it utilizes a stacked neural network combining Gaussian Process Regression (GPR) and Multilayer Perceptron (MLP) to capture luminance features under low illumination and to process nonlinear characteristics across different light levels. By integrating the multiscale hybrid features of GPR with the perceptual capabilities of MLP and fusing through Random Forest, it achieves high precision calibration and a wide range under limited data samples. Second, for chromaticity calibration, it employs the Adaptive Multidimensional Color Space Transformation Network (AMCS-TransNet), expanding the dimensions of the color space and incorporating a linear transformation layer with a dynamic learning matrix to enhance the stability of color space conversion. This ensures accurate conversion from RGB to CIE XYZ space, adaptable to white points across different dimensions. LumChromNet extends the luminance grayscale range to 0-255, with a fitting error below 1.87%), and enhances color space R2 to 0.998 with an average error within 1.5%). It expands the luminance measurement range to 0-250 cd/m2and maintains optical property errors under pm 5%, providing a cost-effective, flexible, and automated strategy for VR glasses and other devices. © 2024 IEEE.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Source identification and prediction of nitrogen and phosphorus pollution of Lake Taihu by an ensemble machine learning technique

引用

Frontiers of Environmental Science & engineering 2023年第5期17卷 27-40页

作者： Yirong Hu Wenjie Du Cheng Yang Yang Wang Tianyin Huang Xiaoyi Xu Wenwei Li CAS Key Laboratory of Urban Pollutant Conversion Department of Environmental Science and EngineeringUniversity of Science and Technology of ChinaHefei 230026China School of Software Engineering University of Science and Technology of ChinaHefei 230026China USTC-CityU Joint Advanced Research Center Suzhou Institute for Advanced Research of USTCSuzhou 215123China National and Local Joint Engineering Laboratory for Municipal Sewage Resource Utilization Technology Suzhou University of Science and TechnologySuzhou 215009China

Effective control of lake eutrophication necessitates a full understanding of the complicated nitrogen and phosphorus pollution sources,for which mathematical modeling is commonly *** contrast to the conventional knowledge-based models that usually perform poorly due to insufficient knowledge of pollutant geochemical cycling,we employed an ensemble machine learning(ML)model to identify the key nitrogen and phosphorus sources of *** ML models were developed based on 13 years of historical data of Lake Taihu’s water quality,environmental input,and meteorological conditions,among which the XGBoost model stood out as the best model for total nitrogen(TN)and total phosphorus(TP)*** results suggest that the lake TN is mainly affected by the endogenous load and inflow river water quality,while the lake TP is predominantly from endogenous *** prediction of the lake TN and TP concentration changes in response to these key feature variations suggests that endogenous source control is a highly desirable option for lake eutrophication ***,one-month-ahead prediction of lake TN and TP concentrations(R2 of 0.85 and 0.95,respectively)was achieved based on this model with sliding time window lengths of 9 and 6 months,*** work demonstrates the great potential of using ensemble ML models for lake pollution source tracking and prediction,which may provide valuable references for early warning and rational control of lake eutrophication.

关键词： Eutrophication Machine learning Water quality Nutrients Prediction

来源：评论

学校读者我要写书评

暂无评论

WASMDYPA: Effectively Detecting WebAssembly Bugs via Dynamic Program Analysis 31

WASMDYPA: Effectively Detecting WebAssembly Bugs via Dynamic...

引用

31st IEEE International Conference on software Analysis, Evolution and Reengineering, SANER 2024

作者： Zheng, Wenlong Hua, Baojian School of Software Engineering University of Science and Technology of China Suzhou Institute for Advanced Research University of Science and Technology of China China

ISBN: (纸本)9798350330663

Safe binary execution is often a crucial requirement in today's security critical computing infrastructures. WebAssembly is an emerging language designed for safe binary execution that has been deployed in many security critical domains, such as blockchain, edge computing, and clouds. However, WebAssembly's security guarantee is not a cure-all, and recent studies have revealed a large spectrum of security issues such as integer overflows and memory vulnerabilities, leading to serious security hazards to WebAssembly applications. In this paper, we propose the first automated bug detection framework for WebAssembly programs based on dynamic program analysis, directly on WebAssembly binaries. To realize the whole process, we present WASMDYPA, the dynamic bug detection system, consisting of three primary components: 1) an input generator for WebAssembly binaries;2) a static instrumentation hook providing extensible interfaces to collect runtime information;and 3) dynamic program analysis algorithms as security plugins to detect vulnerabilities. We have implemented a software prototype for WASMDYPA, and have conducted experiments to evaluate the effectiveness, usefulness, performance and overhead of our approach. Experimental results demonstrated that WASMDyPA can accurately detect vulnerabilities with a 88.24% precision and a 93.75% recall. Furthermore, WAS-MDyPA detected 56 bugs in real-world WebAssembly programs, including 2 integer overflows and 54 memory bugs. © 2024 IEEE.

关键词： software prototyping

来源：评论

学校读者我要写书评

暂无评论

Long-Lasting Filtration of Oily Water by Anti-Fouling Underwater Oleophobic Sand Particles

引用

Journal of Bionic engineering 2024年第2期21卷 913-923页

作者： Xingyu Liu Junxu Chen Rui Wang Yifan Su Zhangheng Zhou Zezhong Hou Zhuoran Li Junhao Zhao Weicai Shi Xinquan Yu Zhaopeng Yu Youfa Zhang State Key Laboratory of Advanced Technology for Float Glass CNBM Research Institute for Advanced Glass Materials Group Co.LtdBengbu233000China Jiangsu Key Laboratory of Advanced Metallic Materials School of Materials Science and EngineeringSoutheast UniversityNanjing211189China Research Institute of Petroleum Engineering Technology of Jiangsu Oilfield Yangzhou225009China Kunshan Industrial Technology Research Institute Kunshan215300SuzhouChina School of Automotive Engineering Changshu Institute of TechnologyChangshu215500SuzhouChina

The produced water from the oilfield was purified with filter material and then injected back into the *** serpentine filter material was easy to harden with the increase in filtration amount,which affected the water quality.A superhydrophilic/underwater oleophobic serpentine filter material was successfully prepared by a simple method of coating modification,which exhibited long-lasting filtration of oily water,good filtration and anti-fouling properties,and resistance to *** film-forming material of the superhydrophilic/underwater oleophobic coating was composed of SiO_(2) particles with small size,which could completely and evenly cover the filter *** weight loss was only 7.6%after mechanical stirring for 90 *** with the original filter material,the superhydrophilic/underwater oleophobic serpentine filter material showed a better anti-fouling ability and resistance to *** filtration of crude oil emulsion and oil slick sewage showed a better backwashing *** 35 cycles of continuous filtration of suspended solids in wastewater,the backwashing rate reached 78.4%.The results provided an effective method for the filtration of oily wastewater in the oilfield.

关键词： Serpentine Underwater oleophobic Water immersion resistance Anti-fouling Hardening resistance

来源：评论

学校读者我要写书评

暂无评论

A Review of Intelligent Configuration and Its Security for Complex Networks

引用

Chinese Journal of Electronics 2024年第4期33卷 920-947页

作者： Yue ZHAO Bin YANG Fei TENG Xianhua NIU Ning HU Bo TIAN Science and Technology on Communication Security Laboratory School of Computer and Information Engineering Chuzhou University School of Computing and Artificial Intelligence Southwest Jiaotong University School of Computer and Software Engineering Xihua University Cyberspace Institute of Advanced Technology Guangzhou University

Complex networks are becoming more complex because of the use of many components with diverse technologies. In fact, manual configuration that makes each component interoperable has breed latent danger to system security. There is still no comprehensive review of these studies and prospects for further research. According to the complexity of component configuration and difficulty of security assurance in typical complex networks, this paper systematically reviews the abstract models and formal analysis methods required for intelligent configuration of complex networks, specifically analyzes, and compares the current key technologies such as configuration semantic awareness, automatic generation of security configuration, dynamic deployment, and verification evaluation. These technologies can effectively improve the security of complex networks intelligent configuration and reduce the complexity of operation and maintenance. This paper also summarizes the mainstream construction methods of complex networks configuration and its security test environment and detection index system, which lays a theoretical foundation for the formation of the comprehensive effectiveness verification capability of configuration security. The whole lifecycle management system of configuration security process proposed in this paper provides an important technical reference for reducing the complexity of network operation and maintenance and improving network security.

关键词： Complex networks Intelligent configuration Configuration security software defined network Lifecycle management

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：