检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Berger, Harel Dvir, Amit Hajaj, Chen Ariel Cyber Innovation Center Computer Science Department Ariel University 65 Ramat HaGolan street Ariel Israel Ariel Cyber Innovation Center Data Science and Artificial Intelligence Research Center Industrial Engineering and Management Department Ariel University 65 Ramat HaGolan street Ariel Israel

Android is the most popular OS worldwide. Therefore, it is a target for various kinds of malware. As a countermeasure, the security community works day and night to develop appropriate Android malware detection systems, with ML-based or DL-based systems considered as some of the most common types. Against these detection systems, intelligent adversaries develop a wide set of evasion attacks, in which an attacker slightly modifies a malware sample to evade its target detection system. In this survey, we address problem-space evasion attacks in the Android OS, where attackers manipulate actual APKs, rather than their extracted feature vector. We aim to explore these kind of attacks, frequently overlooked by the research community due to a lack of knowledge of the Android domain, or due to focusing on general mathematical evasion attacks - i.e., feature-space evasion attacks. We discuss the different aspects of problem-space evasion attacks, using a new taxonomy, which focuses on key ingredients of each problem-space attack, such as the attacker model, the attacker's mode of operation, and the functionality assessment of post-attack applications. © 2022, CC BY.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Leader-following cooperative guidance law with specified impact time

引用

science China(Technological sciences) 2020年第11期63卷 2349-2356页

作者： LI GuoFei LI Qing WU YunJie XU PengYa LIU JianWei School of Cyber Science and Technology Beihang UniversityBeijing 100191China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China Beijing Advanced Innovation Center for Big Data and Brain Machine Intelligence Beihang UniversityBeijing 100083China

The problem of guidance law is investigated for multiple interceptors to attack a target cooperatively.A leader-following cooperative guidance strategy is presented to render the leader and the followers reach the target at specified impact *** guidance law of leader is given to meet the demand of specified impact *** arrival time is synchronized by enforcing the ranges-to-go of followers keep consensus with that of *** convergence time bound is estimated without dependence on the initial states,since the proposed leader-following cooperative guidance law is fixed-time *** simulation is developed to validate the availability of proposed cooperative guidance law.

关键词： cooperative guidance leader-following specified impact time fixed-time convergence

来源：评论

学校读者我要写书评

暂无评论

MaMaDroid2.0 - The Holes of Control Flow Graphs

arXiv

引用

arXiv 2022年

作者： Berger, Harel Hajaj, Chen Mariconti, Enrico Dvir, Amit Ariel Cyber Innovation Center Computer Science Department Ariel University Ariel Israel Ariel Cyber Innovation Center Data Science and Artificial Intelligence Research Center Industrial Engineering and Management Department Ariel University Ariel Israel Jill Dando Institute Department of Security and Crime Science UCL London United Kingdom

Android malware is a continuously expanding threat to billions of mobile users around the globe. Detection systems are updated constantly to address these threats. However, a backlash takes the form of evasion attacks, in which an adversary changes malicious samples such that those samples will be misclassified as benign. This paper fully inspects a well-known Android malware detection system, MaMaDroid, which analyzes the control flow graph of the application. Changes to the portion of benign samples in the train set and models are considered to see their effect on the classifier. The changes in the ratio between benign and malicious samples have a clear effect on each one of the models, resulting in a decrease of more than 40% in their detection rate. Moreover, adopted ML models are implemented as well, including 5-NN, Decision Tree, and Adaboost. Exploration of the six models reveals a typical behavior in different cases, of tree-based models and distance-based models. Moreover, three novel attacks that manipulate the CFG and their detection rates are described for each one of the targeted models. The attacks decrease the detection rate of most of the models to 0%, with regards to different ratios of benign to malicious apps. As a result, a new version of MaMaDroid is engineered. This model fuses the CFG of the app and static analysis of features of the app. This improved model is proved to be robust against evasion attacks targeting both CFG-based models and static analysis models, achieving a detection rate of more than 90% against each one of the attacks. © 2022, CC BY.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

TreeXGNN: can gradient-boosted decision trees help boost heterogeneous graph neural networks?

TreeXGNN: can gradient-boosted decision trees help boost het...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ming-Yi Hong Shih-Yen Chang Hao-Wei Hsu Yi-Hsiang Huang Chih-Yu Wang Che Lin Graduate Program of Data Science National Taiwan University and Academia Sinica Taiwan Graduate Institute of Communication Engineering National Taiwan University Taiwan Research Center for Information Technology Innovation Academia Sinica Taiwan Department of Electrical Engineering National Taiwan University Taiwan

Graph neural networks are a promising deep learning method that can apply graph structures to various tasks. In real-world scenarios, we often have heterogeneous graphs, wherein different node and edge types capture complex interactions between nodes. High-dimensional node features provide rich information about the target nodes. Conventional heterogeneous graph neural networks (HGNN) focus more on graph structures than node features and may have difficulties extracting knowledge from complex node features. In this study, we propose a novel framework, the tree-boosted heterogeneous graph neural network abbreviated as TreeXGNN, which could efficiently and automatically extract target node features via gradient-boosted decision trees (GBDT). It integrates community structure information with proper fusion modules and a shared feature space design on HGNN. We achieved state-of-the-art performance on the three well-known heterogeneous graph benchmark datasets, IMDB, DBLP, and ACM, and significantly improved performance compared to previous studies. Our work paves the foundation for integrating tree-based models to boost HGNNs for general community analysis.

关键词： Training Knowledge engineering Deep learning Signal processing Feature extraction Graph neural networks Decision trees

来源：评论

学校读者我要写书评

暂无评论

Corrosion-resistant aluminum alloy design through machine learning combined with high-throughput calculations

arXiv

引用

arXiv 2023年

作者： Ji, Yucheng Fu, Xiaoqian Ding, Feng Xu, Yongtao He, Yang Ao, Min Xiao, Fulai Chen, Dihao Dey, Poulumi Xiao, Kui Ren, Jingli Li, Xiaogang Dong, Chaofang Ji, Y. Fu, X. Ding, F. He, Y. Ao, M. Chen, D. Xiao, K. Li, X. Dong, C. Ji, Y. Dey, P. Xu, Y. Xiao, F. Ren, J. Beijing Advanced Innovation Center for Materials Genome Engineering National Materials Corrosion Protection Data Center Institute for Advanced Materials and Technology Shunde Innovation School University of Science and Technology Beijing Beijing100083 China Department of Materials Science and Engineering Faculty of Mechanical Maritime and Materials Engineering Delft University of Technology Delft2628CD Netherlands National Engineering & Technology Research Center for Non-Ferrous Metals Composites GRINM Group Corporation Limited Beijing101407 China Shandong Nanshan Aluminum Co. Ltd. Longkou265706 China Henan Academy of Big Data Zhengzhou University Zhengzhou450001 China

Efficiently designing lightweight alloys with combined high corrosion resistance and mechanical properties remains an enduring topic in materials engineering. To this end, machine learning (ML) coupled ab-initio calculations is proposed within this study. Due to the inadequate accuracy of conventional stress-strain ML models caused by corrosion factors, a novel reinforcement self-learning ML algorithm (accuracy R2 >0.92) is developed. Then, a strategy that integrates ML models, calculated energetics and mechanical moduli is implemented to optimize the Al alloys. Next, this Computation Designed Corrosion-Resistant Al alloy is fabricated that verified the simulation. The performance (elongation reaches ~30%) is attributed to the H-captured Al-Sc-Cu phases (-1.44 eV H-1) and Cu-modified η/η' precipitation inside the grain boundaries (GBs). The developed Al-Mg-Zn-Cu interatomic potential (energy accuracy 6.50 meV atom-1) proves the cracking resistance of the GB region enhanced by Cu-modification. Conceptually, our strategy is of practical importance for designing new alloys exhibiting corrosion resistance and mechanical properties. Copyright © 2023, The Authors. All rights reserved.

关键词： Aluminum alloys

来源：评论

学校读者我要写书评

暂无评论

Elevating the photodecolorization efficiency for synthetic and actual colored wastewater through the integration of chitosan and zinc oxide layers on a fiberglass flat sheets

引用

Case Studies in Chemical and Environmental engineering 2024年 10卷

作者： Subagyo, Riki Saepurahman, Saepurahman Zain, Elfirza Hartati, Sri Zhang, Lei Kurnia, Kiki Adi Arramel, Arramel Ediati, Ratna Akhlus, Syafsir Kusumawati, Yuly Department Chemistry Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Research Center for Chemistry National Research and Innovation Agency (BRIN) Center of Excellence Applied Physics and Chemistry Nano Center Indonesia Departement of Physics National University of Singapore Department of Chemical Engineering Bandung Institute of Technology

This study reported a novel technique for spray coating zinc oxide (ZnO) on one side of fiberglass (FG) substrate and chitosan (CS) on the opposite side, resulting in the production of ZnO/FG/CS composite. This strategy alters the morphology of the pure FG, creating smooth and rough surfaces on the CS and ZnO sides, respectively. ZnO/FG/CS demonstrated remarkable photoremoval activity in a combined solution of methylene blue-methyl orange and real wastewater with the addition of hydrogen peroxide and facilitated moderate reusability over five cycles. This strategy revealed an insight for developing an integrated adsorption and photocatalytic process with high-performance capabilities. © 2024 The Authors

关键词： Chitosan Composite Photodecolorization Wastewater ZnO

来源：评论

学校读者我要写书评

暂无评论

Modeling viral evolution:A novel SIRSVIDE framework with application to SARS-CoV-2 dynamics

微生物与宿主健康（英文）

引用

微生物与宿主健康（英文） 2024年第5期2卷 227-245页

作者： Kaichun Jin Xiaolu Tang Zhaohui Qian Zhiqiang Wu Zifeng Yang Tao Qian Chitin Hon Jian Lu State Key Laboratory of Protein and Plant Gene Research Center for BioinformaticsSchool of Life SciencesPeking UniversityBeijingChina NHC Key Laboratory of Systems Biology of Pathogens Institute of Pathogen BiologyChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina State Key Laboratory of Respiratory Disease National Clinical Research Center for Respiratory DiseaseGuangzhou Institute of Respiratory HealthThe First Affiliated Hospital of Guangzhou Medical UniversityGuangdongChina Respiratory Disease Al Laboratory on Epidemic and Medical Big Data Instrument Applications Department of Engineering ScienceFaculty of Innovation EngineeringMacau University of Science and TechnologyMacauChina Guangzhou Key Laboratory for Clinical Rapid Diagnosis and Early Warning of Infectious Diseases KingMed School of Laboratory MedicineGuangzhou Medical UniversityGuangdongChina Guangzhou Key Laboratory for Clinical Rapid Diagnosis and Early Warning of Infectious Diseases KingMed School of Laboratory MedicineGuangzhou Medical UniversityGuangdongChina Macau Center for Mathematical Sciences Macau University of Science and TechnologyMacauChina Respiratory Disease Al Laboratory on Epidemic and Medical Big Data Instrument Applications Department of Engineering ScienceFaculty of Innovation EngineeringMacau University of Science and TechnologyMacauChina Guangzhou Key Laboratory for Clinical Rapid Diagnosis and Early Warning of Infectious Diseases KingMed School of Laboratory MedicineGuangzhou Medical UniversityGuangdongChina Department of Engineering Science Faculty of Innovation EngineeringMacau University of Science and TechnologyMacauChina

Understanding evolutionary trends in emerging viruses,such as severe acute respiratory syndrome coronavirus 2(SARS-CoV-2),is crucial for effective public health management and ***,extensive debates have arisen concerning viral evolutionary trends,particularly the interplay between transmissibility,pathogenicity,and im-mune *** this context,we have developed a novel computational model named SIRSVIDE(Susceptible-In-fected-Recovered-Susceptible-Variation-Immune Decay-Immune Escape)to simulate the transmission and evolu-tionary dynamics of viral *** simulation results indicate that under conditions of high mutation rates,elevated transmission rates,and larger susceptible host populations,viral populations exhibit prolonged increases in transmissibility and immune escape,accompanied by reductions in pathogenicity and noticeable short-term ***,when the total susceptible population size and mutation rate decrease,substantial uncertainty in the evolutionary trends of viral populations becomes *** summary,the SIRSVIDE model establishes a comprehen-sive framework for generating both short-and long-term viral epidemiological and evolutionary *** simula-tion outcomes align with existing evidence indicating that SARS-CoV-2 is undergoing selection for heightened trans-missibility,decreased pathogenicity,and enhanced immune ***,the model sheds light on the possible evolutionary dynamics of other viruses.

关键词： viral evolution severe acute respiratory syndrome coronavirus 2(SARS-CoV-2) transmissibility-pathogenicity trade-off immune escape

来源：评论

学校读者我要写书评

暂无评论

Effects of NGF-chitosan on alleviating secondary degeneration and repairing primary degeneration after expanded partial optic nerve transection

引用

science China Life sciences 2025年

作者： Xiao Liu Hongmei Duan Limin Gao Linhao Yuan Peng Hao Wen Zhao Yudan Gao Zitian Huang Xi Wang Wenjianlong Zhou Shunchang Ma Ningli Wang Kwok-Fai So Zhaoyang Yang Xiaoguang Li Wang Jia School of Engineering Medicine Beijing Key Laboratory for Biomaterials and Neural Regeneration Beihang University Beijing International Cooperation Bases for Science and Technology on Biomaterials and Neural Regeneration Beijing Advanced Innovation Center for Big Data-Based Precision MedicineBeihang University China National Clinical Research Center for Neurological Diseases (NCRC-ND) Department of Neurosurgery Beijing Tiantan Hospital National Center for Neurological Disorders Capital Medical University Department of Neurobiology School of Basic Medical Sciences Capital Medical University Department of Neurotomy Beijing Neurosurgical Institute Capital Medical University Beijing Tongren Eye Center Beijing Tongren Hospital Capital Medical University Beijing Ophthalmology and Visual Sciences Key Laboratory Guangdong-Hongkong-Macau Institute of CNS Regeneration Ministry of Education CNS Regeneration Collaborative Joint Laboratory Jinan University Bioland Laboratory (Guangzhou Regenerative Medicine and Health Guangdong Laboratory) Department of Ophthalmology and State Key Laboratory of Brain and Cognitive Sciences The University of Hong Kong Center for Brain Science and Brain-Inspired Intelligence Guangdong-Hong Kong-Macao Greater Bay Area Co-innovation Center of Neuroregeneration Nantong University

Optic neuropathy is one of the main causes of irreversible blindness in the world, and there is no effective treatment in clinic. Both primary degeneration and secondary degeneration play an important role in the injury caused by optic neuropathy. Partial optic nerve transection(PONT) model can be used to study these two kinds of degeneration simultaneously. However, there is currently no measure that can effectively intervene in both types of injuries concurrently. Here, we constructed an expanded partial optic nerve transection(EPONT) model. Nerve growth factor(NGF)-chitosan locally implanted into the injured area could simultaneously intervene in the secondary and primary degeneration, not only protecting the ventral part of the injured optic nerve, but also promoting the regeneration of the dorsal part. Visual functions, including pupillary light reflex and depth perception, were also well preserved. NGF-chitosan exerted biological effects by enhancing the expression of NGF and tyrosine kinase A(Trk A) in the optic nerve and retinal ganglion cells(RGCs). Furthermore, NGFchitosan played a protective and repairing role by inhibiting the activation of microglia in the ventral area of the injured optic nerve and increasing the expression of mammalian target of rapamycin(m TOR) in RGCs. Our results demonstrate that the local use of NGF-chitosan in the injured area effectively repaired the optic nerve, which provides a new measure for the clinical treatment of optic nerve injury.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed time-varying formation control with uncertainties based on an event-triggered mechanism

引用

science China(Information sciences) 2021年第3期64卷 167-176页

作者： Xiaoduo LI Yumeng BAI Xiwang DONG Qingdong LI Zhang REN Science and Technology on Aircraft Control Laboratory School of Automation Science and Electrical EngineeringBeihang University Department of Electrical and Computer Engineering University of Wisconsin-Madison Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

This paper investigates the distributed time-varying formation(TVF) problems for general linear multi-agent systems(MASs) subject to matched bounded uncertainties based on an adaptive event-triggered mechanism. A TVF protocol was designed with an event-triggered mechanism by introducing adaptive weights into the formation control protocol and triggering condition, and the large chattering phenomenon was avoided by the σ-modification adaptive law. According to the Lyapunov stability theory, proof has been established that the MASs in the presence of uncertainties can realize the expected formation that satisfies the given feasible condition. Finally, an example is provided to verify the effectiveness of the proposed algorithm.

关键词： formation control multi-agent systems event-triggered adaptive control

来源：评论

学校读者我要写书评

暂无评论

Detection of oil spill based on CBF-CNN using HY-1C CZI multispectral images

引用

Acta Oceanologica Sinica 2022年第7期41卷 166-179页

作者： Kai Du Yi Ma Zongchen Jiang Xiaoqing Lu Junfang Yang College of Geodesy and Geomatics Shandong University of Science and TechnologyQingdao266590China First Institute of Oceanology Ministry of Natural ResourcesQingdao266061China School of Electronics and Information Engineering Harbin Institute of TechnologyHarbin150001China National Satellite Ocean Application Service Beijing100081China College of Oceanography and Space Informatics China University of Petroleum(East China)Qingdao266580China Technology Innovation Center for Ocean Telemetry Ministry of Natural ResourcesQingdao266061China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710072China

Accurate detection of an oil spill is of great significance for rapid response to oil spill *** images have the advantages of high spatial resolution,short revisit period,and wide imaging width,which is suitable for large-scale oil spill ***,in wide remote sensing images,the number of oil spill samples is generally far less than that of seawater ***,the sea surface state tends to be heterogeneous over a large area,which makes the identification of oil spills more difficult because of various sea conditions and *** address this problem,we used the F-Score as a measure of the distance between forecast value and true value,proposed the Class-Balanced F loss function(CBF loss function)that comprehensively considers the precision and recall,and rebalances the loss according to the actual sample numbers of various *** the CBF loss function,we constructed convolution neural networks(CBF-CNN)for oil spill *** on the image acquired by the Coastal Zone Imager(CZI)of the Haiyang-1C(HY-1C)satellite in the Andaman Sea(study area 1),we carried out parameter adjustment *** contrast to experiments of different loss functions,the F1-Score of the detection result of oil emulsions is 0.87,which is 0.03–0.07 higher than cross-entropy,hinge,and focal loss functions,and the F1-Score of the detection result of oil slicks is 0.94,which is 0.01–0.09 higher than those three loss *** comparison with the experiment of different methods,the F1-Score of CBF-CNN for the detection result of oil emulsions is 0.05–0.12 higher than that of the deep neural networks,supports vector machine and random forests models,and the F1-Score of the detection result of oil slicks is 0.15–0.22 higher than that of the three *** verify the applicability of the CBF-CNN model in different observation scenes,we used the image obtained by HY-1C CZI in the Karimata Strait to carry out experiments,which include two stu

关键词： oil spills CNN classification loss function sunglint detection

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：