检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Robust Android Malware Familial Classification

arXiv

引用

arXiv 2021年

作者： Wu, Yueming Dou, Shihan Zou, Deqing Yang, Wei Qiang, Weizhong Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China University of Texas at Dallas Dallas United States National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware family analysis can be achieved through contrastive learning. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and other types of malware. Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps can be obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining a 98.4% F1 on classifying 69,421 obfuscated malware samples. © 2021, CC0.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

An efficient i(○)-based data integrity verification scheme for cloud storage

引用

中国科学：信息科学（英文版） 2019年第5期62卷 233-235页

作者： Lixue SUN Chunxiang XU Yuan ZHANG Kefei CHEN Center for Cyber Security School of Computer Science and EngineeringUniversity of Electronic Science and Technology of China Chengdu 611731 China Center for Cyber Security School of Computer Science and EngineeringUniversity of Electronic Science and Technology of China Chengdu 611731 China Department of Electrical and Computer Engineering University of Waterloo Waterloo N2L 3G1 Canada School of Science Hangzhou Normal University Hangzhou 310036 China

Dear editor, With the advent of big data,an increasing number of people are storing their data on remote cloud *** storage services enable users to flexibly maintain and access their data via mobile or wireless ***,despite these benefits,cloud storage deprives users of physical control over their data,which poses new challenges in data security [1-4].Data integrity protection is one of the most important of these security challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Decoding Mechanisms for UAV-enabled Double-Uplink Coordinated NOMA

arXiv

引用

arXiv 2022年

作者： Nguyen, Thanh Luan Kaddoum, Georges Do, Tri Nhu da Costa, Daniel Benevides Haas, Zygmunt J. Université du Québec MontréalQCH3C 1K3 Canada Cyber Security Systems and Applied AI Research Center Lebanese American University Lebanon The Technology Innovation Institute Masdar City Abu Dhabi9639 United Arab Emirates The Department of Computer Science University of Texas at Dallas RichardsonTX75080 United States The School of Electrical and Computer Engineering Cornell University IthacaNY14853 United States

In this paper, we propose a novel adaptive decoding mechanism (ADM) for the unmanned aerial vehicle (UAV)enabled uplink (UL) non-orthogonal multiple access (NOMA) communications. Specifically, considering a harsh UAV environment, where ground-to-ground links are regularly unavailable, the proposed ADM overcomes the challenging problem of conventional UL-NOMA systems whose performance is sensitive to the transmitter's statistical channel state information and the receiver's decoding order. To evaluate the performance of the ADM, we derive closed-form expressions for the system outage probability (OP) and system throughput. In the performance analysis section, we provide novel expressions for practical air-to-ground and ground-to-air channels, while taking into account the practical implementation of imperfect successive interference cancellation (SIC) in UL-NOMA. Moreover, the obtained expression can be adopted to characterize the OP of various systems under a Mixture of Gamma (MG) distribution-based fading channels. Next, we propose a sub-optimal Gradient Descent-based algorithm to obtain the power allocation coefficients that result in maximum throughput with respect to each location on UAV's trajectory. To determine the significance of the proposed ADM in nonstationary environments, we consider the ground users and the UAV to move according to the Random Waypoint Mobility (RWM) and Reference Point Group Mobility (RPGM) models, respectively. Accurate formulas for the distance distributions are also provided. Numerical solutions demonstrate that the ADM-enhanced NOMA not only outperforms Orthogonal Multiple Access (OMA), but also improves the performance of UAV-enabled UL-NOMA even in mobile environments. © 2022, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Heart Disease Prediction Using Machine Learning Method

Heart Disease Prediction Using Machine Learning Method

引用

cyber Resilience (ICCR), International Conference on

作者： Mafia Rasheed Muhammad Adnan Khan Nouh Sabri Elmitwally Ghassan F. Issa Taher M. Ghazal Hamza Alrababah Beenu Mago Department of Computer Science Agriculture University Faisalabad Pakistan Faculty of Computing Riphah School of Computing & Innovation Riphah International University Lahore Pakistan Faculty of Computing Engineering and the Built Environment Birmingham City University Birmingham United Kingdom School of Information Technology Skyline University College University City Sharjah Sharjah UAE Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia (UKM) Bangi Selangor Malaysia School of Information Technology Skyline University College Sharjah UAE

ISBN: (数字)9781665461221

ISBN: (纸本)9781665461238

The heart disease is also known as coronary artery disease, many hearts affecting symptoms that are very common nowadays and causes death. It is a challenging task to diagnose heart diseases without any intelligent diagnosing system. Many researchers did research on it and developed a diagnostic system to diagnose heart diseases and worked on it. The prediction of cardiovascular disease, required a brief medical history of patients, including genetic information. The world is in acute need of a system for predicting heart disease and it became crucial. Data mining and machine learning are common techniques used in the field of health care to process large and complex data. This research paper presents reasons for heart disease and a model based on Machine learning algorithms for prediction.

关键词： Heart Support vector machines Training data Machine learning Medical services Predictive models Cardiovascular diseases

来源：评论

学校读者我要写书评

暂无评论

A Secure Opus Pulse Steganographic Scheme Based on Message Transform

A Secure Opus Pulse Steganographic Scheme Based on Message T...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Yanzhen Ren Shan Zhong Weiping Tuy Lina Wang Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University

ISBN: (数字)9789881476883

ISBN: (纸本)9781728181301

This paper proposes a secure steganography scheme in Opus pulse domain. Opus is a versatile audio codec designed for interactive Internet applications and is widely used in the Internet communication applications. In Opus pulse domain, there exists a large embedding space, which makes it an ideal carrier for steganography. The challenge is that the generation of pulse samples depends on the value of previous pulse samples, so the embedding operation must be carried out at a single sample, otherwise it will lead to distortion drift. This paper proposes a scheme with message transform and rate-distortion evaluation to improve statistical security. The experiment results show that the proposed scheme achieves good auditory quality and statistical security with a large embedding capacity.

关键词： Quantization (signal) Codecs Rate-distortion Markov processes Histograms Delays Viterbi algorithm

来源：评论

学校读者我要写书评

暂无评论

FedMLC: White-box Model Watermarking for Copyright Protection in Federated Learning for IoT Environment

引用

IEEE Internet of Things Journal 2025年

作者： Chen, Weitong Zhang, Wei Wu, Di Keskinarkaus, Anja Seppanen, Tapio Zhang, Jiale Gao, Longxiang Luan, Tom H. Yangzhou University School of Information Engineering Yangzhou225009 China ToowoombaQLD4350 Australia University of Oulu Physiological Signal Analysis Team Center for Machine Vision and Signal Analysis Oulu90014 Finland University of Southern Queensland SoMPC ToowoombaQLD4350 Australia Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China Xi'an Jiaotong University School of Cyber Science and Engineering Xi'an710049 China

With the widespread application of the Internet of Things (IoT), data processing has gradually migrated to edge devices that are closer to the data source. This shift has significantly improved the ability of real-time data analysis while effectively reducing bandwidth requirements and latency. Furthermore, Federated Learning (FL) has been introduced as a decentralized training method to achieve collaborative training of multiple devices while ensuring local data privacy. However, malicious clients in FL may theft trained models for unauthorized use, which causes model misuse or copyright challenges. To address these issues, this paper proposes FedMLC (Malicious client detection, Leakage tracing, and Copyright verification), a server-side white-box watermarking scheme. FedMLC utilizes the embedded watermark at different stages to achieve both traceability and copyright verification, simplifying the watermarking process. Additionally, the watermarking can also detect malicious clients in FL. Specifically, FedMLC uses the regularization term to guide the parameter signs of the normalization layer to be consistent with the watermark sign, thereby achieving watermark embedding. Experimental results show that our FL model watermarking scheme excels in malicious client detection, leakage tracing, and copyright verification, with minimal impact on model performance, able to resist various attacks such as fine-tuning, pruning, and quantization. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Secure searchable public key encryption against insider keyword guessing attacks from indistinguishability obfuscation

引用

science China(Information sciences) 2018年第3期61卷 228-230页

作者： Lixue SUN Chunxiang XU Mingwu ZHANG Kefei CHEN Hongwei LI Center for Cyber Security School of Computer Science and EngineeringUniversity of Electronic Science and Technology of China School of Computer Science Hubei University of Technology School of Science Hangzhou Normal University Laboratory of Science and Technology on Communication Security

Public key encryption with keyword search(PEKS)enables one to search encrypted data containing some keyword without decrypting the data in public key *** et al.[1]introduced the notion of PEKS,but later Byun et al.[2]showed the scheme in[1]is vulnerable to the outsider/insider keyword guessing attacks(KGA).Many previous PEKS studies have tackled the

关键词： SKS IND PKI MAC SKR Mac PKR

来源：评论

学校读者我要写书评

暂无评论

A systematic review of bio-cyber interface technologies and security issues for internet of bio-nano things

arXiv

引用

arXiv 2021年

作者： Zafar, Sidra Nazir, Mohsin Bakhshi, Taimur Ali Khattak, Hasan Khan, Sarmadullah Bilal, Muhammad Choo, Kim-Kwang Raymond Kwak, Kyung-Sup Sabah, Aneeqa Department of Computer Science Lahore College for Women University Lahore54000 Pakistan Center for Information Management & Cyber Security National University of Computer & Emerging Sciences Lahore Pakistan Islamabad Pakistan School of Computer Science and Informatics De Montfort University LeicasterLE1 9BH United Kingdom Department of Computer Engineering Hankuk University of Foreign Studies Gyeonggi-do Yongin-si17035 Korea Republic of Department of Information Systems and Cyber Security University of Texas San AntonioTX78249 United States Department of Information and Communication Engineering Inha University Incheon22212 Korea Republic of Department of Physics Lahore College for Women University Lahore54000 Pakistan

Advances in synthetic biology and nanotechnology have contributed to the design of tools that can be used to control, reuse, modify, and re-engineer cells’ structure, as well as enabling engineers to effectively use biological cells as programmable substrates to realize Bio-NanoThings (biological embedded computing devices). Bio-NanoThings are generally tiny, non-intrusive, and concealable devices that can be used for in-vivo applications such as intra-body sensing and actuation networks, where the use of artificial devices can be detrimental. Such (nano-scale) devices can be used in various healthcare settings such as continuous health monitoring, targeted drug delivery, and nano-surgeries. These services can also be grouped to form a collaborative network (i.e., nanonetwork), whose performance can potentially be improved when connected to higher bandwidth external networks such as the Internet, say via 5G. However, to realize the IoBNT paradigm, it is also important to seamlessly connect the biological environment with the technological landscape by having a dynamic interface design to convert biochemical signals from the human body into an equivalent electromagnetic signal (and vice versa). This, unfortunately, risks the exposure of internal biological mechanisms to cyber-based sensing and medical actuation, with potential security and privacy implications. This paper comprehensively reviews bio-cyber interface for IoBNT architecture, focusing on bio-cyber interfacing options for IoBNT like biologically inspired bio-electronic devices, RFID enabled implantable chips, and electronic tattoos. This study also identifies known and potential security and privacy vulnerabilities and mitigation strategies for consideration in future IoBNT designs and implementations. © 2021, CC BY.

关键词： Thermoelectric equipment

来源：评论

学校读者我要写书评

暂无评论

The Metaverse: Survey, Trends, Novel Pipeline Ecosystem & Future Directions

arXiv

引用

arXiv 2023年

作者： Sami, H. Hammoud, A. Arafeh, M. Wazzeh, M. Arisdakessian, S. Chahoud, M. Wehbi, O. Ajaj, M. Mourad, A. Otrok, H. Abdel Wahab, O. Mizouni, R. Bentahar, J. Talhi, C. Dziong, Z. Damiani, E. Guizani, M. Concordia Institute for Information Systems Engineering Concordia University MontréalQC Canada Department of Electrical Engineering École de Technologie Supérieure Montréal Canada Department of Software and IT engineering École de Technologie Supérieure Montréal Canada Department of Computer and Software Engineering Polytechnique Montréal Montreal Canada Cyber Security Systems and Applied AI Research Center Department of CSM Lebanese American University Beirut Lebanon Division of Science New York University Abu Dhabi United Arab Emirates Department of EECS Khalifa University Abu Dhabi United Arab Emirates Department of ML Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

The Metaverse offers a second world beyond reality, where boundaries are non-existent, and possibilities are endless through engagement and immersive experiences using the virtual reality (VR) technology. Many disciplines can benefit from the advancement of the Metaverse when accurately developed, including the fields of technology, gaming, education, art & culture, socialization, commerce, and businesses. Nevertheless, developing the Metaverse environment to its full potential is an ambiguous task that needs proper guidance and directions. Existing surveys on the Metaverse focus only on a specific aspect and discipline of the Metaverse and lack a holistic view of the entire process. Moreover, most surveys refrain from providing detailed guidance about the development process of the metaverse, including its impact on technologies, businesses, existing challenges, and potential research directions due to their lack of a macro and micro perception of such a topic. To this end, a more holistic, multi-disciplinary, in-depth, and academic and industry-oriented review is required to provide a thorough study of the Metaverse development pipeline and fill the gap in existing Metaverse surveys. To address these issues, we present in this survey a novel multi-layered pipeline ecosystem composed of (1) the Metaverse computing, networking, communications and hardware infrastructure, (2) environment digitization, and (3) user interactions. For every layer, we discuss the components that detail the steps of its development. Also, for each of these components, we examine the impact of a set of enabling technologies and empowering domains (e.g., Artificial Intelligence, security & Privacy, Blockchain, Business, Ethics, and Social) on its advancement. In addition, we explain the importance of these technologies to support decentralization, interoperability, user experiences, interactions, and monetization. Our presented study highlights the existing challenges for each component, fo

关键词： Edge computing

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：