检索结果-内蒙古大学图书馆

5th International Conference on Data Analytics for Business and Industry, ICDABI 2024

作者： Ajayi, Ojo John Sodiya, Adesina Simon Bagiwa, Mustapha Aminu Olowookere, Toluwase Ayobami Department of Cyber Security Abuja Nigeria Federal University of Agriculture Department of Computer Science Abeokuta Nigeria Ahmadu Bello University Department of Computer Science Zaria Nigeria Redeemer's University Department of Computer Science Ede Nigeria

ISBN: (纸本)9798350368710

Governments and corporate institutions are now mostly reliant on integrated digital infrastructures. These digital infrastructures are usually targets of cyber threats such as intrusion, for which intrusion detection systems (IDS) have emerged. One of the key needs for a robust IDS includes reducing the rate of false positives and thus improving accuracy. In this study, three traditional machine learning (ML) algorithms, including K-Nearest Neighbor (KNN), Naive Bayes (NB), and Decision Tree (DT), and three ensemble Machine Learning (ML) algorithms, including Random Forest (RF), Light Gradient Boosting Machine (LGBM), and Extreme Gradient Boosting (XGBOOST), were used on the UNSW-NB15 dataset from the Australian Centre for cyber security's cyber Range Lab, to train intrusion detection models. A super-learner ensemble model was then built using the best two ensemble models (XGBOOST and RF) along with the best traditional model (KNN) as its base learners. The super-learner ensemble model was able to reduce false positives and improve detection accuracy with 98% accuracy. The model was then deployed in an IDS application to mitigate network attacks effectively and efficiently. © 2024 IEEE.

关键词： and xgboost decision tree ids k-nearest neighbour lgbm machine learning naïve bayes random forest super learning

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Nexus: Exploring the Societal Implications of AI-Driven cybersecurity and Data Analysis 13

Unveiling the Nexus: Exploring the Societal Implications of ...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Arif, Mohd Ahmad, Shahnawaz Nazim, Mohd Ahmad, Javed Onyarin, Ogala Justin Galgotias University Department of Computer Science Engineering and Technology Greater Noida India School of Computer Science Engineering and Technology Bennett University Greater Noida India Noida Institute of Engineering and Technology Department of Computer Science Greater Noida India University of Delta Pmb Cyber Security Department Delta State Agbor2090 Nigeria

ISBN: (纸本)9798350380583

AI when integrated with cybersecurity and data analysis forms a new field that will have great impact on the society. The present research focuses on the social consequences of integrating AI for cybersecurity and big data analytics, thus filling the gap in the existing literature. Using both qualitative and quantitative points of view, quantitative analysis and qualitative examination, the research offers an all-embracing understanding of this convergence. It aims to review and analyze the history, present usage, future prognosis of AI related cybersecurity and data analysis, including the reflection of ethical issues, privacy aspects and relevant laws. The lessons learnt are discussed based on case studies, best practices analysis, and the study provides recommendations for the effective use of AI-based solutions throughout their life cycle. The analysis broadens the knowledge on the effects of AI technology for cybersecurity and data analytics, and helps researchers, policymakers, and industry stakeholders apply the new knowledge. © 2024 IEEE.

关键词： cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Crime Against Women in India: Statistical Analysis Using Linear Regression 2

Crime Against Women in India: Statistical Analysis Using Lin...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Mim, Zarin Tasnim Paul, Rittika Foysal, Mollah Md Tohfa, Fairuz Nowshin Mahi, Shah Abrar Bangalore India Bangalore India B-Tech of Computer Science and Engineering East Delta University Chattagram Bangladesh B-Tech of Computer Science and Engineering-Cyber Security Chandigarh University Delhi India

ISBN: (纸本)9798331519056

The crime reports of offenses occurring against women all over India are increasing day by day. It has become one of today's most concerning socio-economic and cultural issues. Crime against women hampers the overall prosperity and development of the nation. This crime violates human rights, impacts women's physical and mental health, and becomes an educational barrier to women's empowerment. This paper surveys the reasons for the influence of reported Crime Against Women (CAW) in 35 states and union territories in India from 2001-2012. The dataset describes different types of Crime Against Women (CAW): rape, kidnapping, abduction, assault on women, insult to the modesty of women, cruelty by husband or relative. This paper also contains a report on the arrested rate for crimes against women in India from 2001-2012. According to the comparison between these two datasets, the person arrest rate is more than the crime against women rate in every state in India. We used machine learning-based linear regression analysis to format the relationship between two datasets, where crime against women is the dependent variable and people arrested rate is the independent variable. This paper discusses two types of linear regression: Simple Linear Regression and Multiple Linear Regression. The relation between these two datasets helps to predict the hot location of crimes, and the activeness of law enforcement regarding the crimes and encourages victims to take action. For the datasets, P-values, R-squared, and adjusted R-squared values are used to evaluate the statistically significant prediction in explaining the variation in crime rates. This prediction is used to reduce the rate of crime against women all over India. © 2024 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection using Domain-Adversarial Training (DANN) with Invariant Risk Minimization (IRM) Hybrid Approach 3

Breast Cancer Detection using Domain-Adversarial Training (D...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Akash, K.V. Daniel, Esther Seetha, S. Durga, S. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India Cmr Institute of Technology Department of Information Science & Engineering India Amrita Vishwa Vidyapeetham Tifac Core in Cyber Security Amrita School of Engineering India

ISBN: (纸本)9798331509675

The breast cancer detection performs a key function in the health care network. The precise and early detection of cancer in the breast could aid to save life of the sufferer. The traditional machine learning methods struggle due to the data used to train is different from data used later this is known as Domain shifts. This project uses a hybrid model known as Domain-Adversarial Training of Neural Networks (DANN) with Invariant Risk Minimization (IRM) Hybrid Method to identification of the tumor in the breast. Through integrating the (DANN) and IRM works perfectly among the various type of data and also with the various image from the various sources. This model is more precise and reliable than any other older *** that this model act as an effective tool for detecting the breast cancer in the early stages. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Designing Biometric Automated Teller Machine: Opportunities and Challenges 4

Designing Biometric Automated Teller Machine: Opportunities ...

引用

4th IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2024

作者： Bastos, João Baptista Muchinenyika, Simon Hlekisana Shava, Fungai Bhunu Nyambuya, Tanaka Mamvura Namibia University of Science and Technology Cyber Security Department Windhoek Namibia Namibia University of Science and Technology Software Engineering Department Windhoek Namibia

ISBN: (纸本)9798331518981

The increasing sophistication of fraud in the financial sector, particularly in Automated Teller Machine (ATM) transactions, demands advanced security measures to protect users and their accounts. Despite the widespread use of Personal Identification Numbers (PINs), literature is replete with evidence that biometric authentication provides better security than PINs. However, a survey on ATMs around the globe shows that biometrics are not widely used for authentication compared to PINs. In an effort to close the gap, this paper presents a two-pronged approach to uncover the challenges and opportunities of their adaptation in Namibia. A literature survey was carried out to establish what is known and identify the gaps. Secondly, some semi-structured qualitative interviews were conducted with purposefully selected key personnel for banks in Namibia and law enforcement agencies to understand ATM security landscape in the country. From these two approaches, biometric designs used in authenticating ATM systems are discussed to unearth strengths and weaknesses that will guide the designing of secure biometric ATM systems. The researchers hope the findings will improve the adoption of biometric security systems, particularly in Namibia, where questionnaires and interviews were administered to ATM experts and the Police. © 2024 IEEE.

关键词： Automatic teller machines

来源：评论

学校读者我要写书评

暂无评论

Using dummy data for RFID tag and reader authentication

引用

Digital Communications and Networks 2022年第5期8卷 804-813页

作者： Baha’A.Alsaify Dale R.Thompson Abdallah Alma'aitah Jia Di Department of Network Engineering and Security Jordan University of Science and TechnologyIrbid21163Jordan Computer Science and Computer Engineering Department University of ArkansasFayetteville72701ARUSA

Radio-Frequency IDentification(RFID)technology is an essential enabler of a multitude of intelligent *** robust authentication of RFID system components is critical in providing trustworthy data delivery from/to *** this paper,we propose an authentication protocol based on monitoring the transmissions between readers and tags in the *** proposed authentication scheme is based on injecting decoys within the exchanged communications(between RFID readers and tags)and is used in the authentication ***,the proposed authentication scheme is mathematically modeled and validated using extensive *** simulations results show that the proposed scheme provides a 100%confidence level in the authentication of tags and detection of compromised readers.

关键词： RFID Authentication Dummy data security Decoys

来源：评论

学校读者我要写书评

暂无评论

APFT: Adaptive Phoneme Filter Template to Generate Anti-Compression Speech Adversarial Example in Real-Time

引用

IEEE Transactions on Information Forensics and security 2025年 20卷 5152-5165页

作者： Huang, Yihuan Ren, Yanzhen Sun, Zongkun Zhai, Liming Wang, Jingmin Liu, Wuyang Wuhan University School of Cyber Science and Engineering Wuhan430072 China Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Central China Normal University School of Computer Science Wuhan430079 China

Automatic Speech Recognition (ASR) systems are widely used for speech censoring. Speech Adversarial Example (AE) offers a novel approach to protect speech privacy by forcing ASR to mistranscribe. However, existing speech AE faces two challenges in real-time voice communication scenarios, such as IP telephone, voice chat, or video conference, it cannot be generated in real-time, and its defensive capability is significantly reduced after the essential audio compression for network transmission. In this paper, we propose Adaptive Phoneme Filter Template (APFT) to address these issues. The key features of APFT include: 1) Phoneme-level Templates for universal AE generation in real-time, 2) Filter, which eliminates redundant signals to improve compression robustness. 3) Adaptive Band Filtering, which limits the attack area from the frequency band without affecting the attack effectiveness and improves speech quality. The comprehensive experimental results show that APFT has four advantages: 1) Real-time Generation, with AE generation time below 1.1ms for 1s speech;2) Compression Robustness, achieving a WER of 0.64 under AAC and Opus codecs;3) Transferability, with an average WER of 0.72 across datasets and ASR systems;4) Stealthiness, achieving a MOS of 4.07 for high-quality speech. In addition, the experiment on Telegram voice calls further proves the practical applicability of APFT. © 2005-2012 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

The Future of Recruitment: Using Deep Learning to Build Intelligent Interview Bots 15

The Future of Recruitment: Using Deep Learning to Build Inte...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Ahmad, Shahnawaz Hussain, Shahadat Wasid, Mohammed Onyarin, Ogala Justin Arif, Mohd Ahmad, Javed Bennett University School of Computer Science Engineering and Technology Greater Noida India University of Delta Cyber Security Department PMB 2090 Delta State Agbor Nigeria Galgotias University Department of Computer Science Engineering and Technology Greater Noida India Sharda University Department of Computer Science Engineering and Technology Greater Noida India

ISBN: (纸本)9798350370249

The hiring process for IT positions is often complex and time-consuming, posing significant challenges for businesses seeking to maintain consistency and efficiency. Interview scheduling is complicated by manual effort and scheduling difficulties, which have been further made worse by the COVID-19 pandemic, making in-person interviews difficult. To address these challenges, this study proposes a Natural Language Processing (NLP)-based Machine Learning (ML) solution that automates interview scheduling and communication in natural language. To develop the solution, two deep-learning NLP models served as the foundation of the system, and AWS serverless stack and Amazon SageMaker were used for training and inference. The solution is designed to be scalable and cost-effective, and new models can be easily added and trained on unique subjects. Furthermore, the Amazon Sumerian scene is customizable to meet branding requirements. This research offers significant implications, as the proposed ML solution can help businesses streamline their hiring process, reduce human error, and improve the accuracy of candidate assessments. The scalability and cost-effectiveness of the solution make it ideal for businesses of all sizes. The smart interview bot developed in this study can conduct live-like interviews that mimic human interactions, making the hiring process more engaging and personalized. Overall, this paper demonstrates the potential of NLP to develop a smart solution for an everyday business problem. The intelligent live-like interview process and smart interview bot developed in this research have the potential to revolutionize the hiring process by automating scheduling and reducing manual effort. By leveraging the proposed ML solution, businesses can improve the accuracy and consistency of their hiring practices, ultimately leading to more successful outcomes. © 2024 IEEE.

关键词： Amazon SOS Amazon Web Services BERT Dynamo DB Machine Learning Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

PriFace: a privacy-preserving face recognition framework under untrusted server

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2967-2979页

作者： Zhao, Shan Zhang, Lefeng Xiong, Ping School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan China Center for Cyber Security and Privacy School of Computer Science University of Technology Sydney Sydney Australia

Alongside the rapid development of artificial intelligence and mobile Internet, face recognition has gradually become a mainstream intelligent terminal authentication technology that is widely applied in security, finance, and social networking, among other fields. However, face images usually contain sensitive personal information, which can have serious consequences for users if this information is leaked or misused. Most existing face privacy protection methods are based on data encryption techniques or differential privacy mechanisms, which make it difficult to strike a good balance between privacy and usability. In this paper, we propose PriFace, a new privacy-preserving method for face recognition based on eigenfaces and locality-sensitive hashing (LSH). PriFace aims to achieve accurate and efficent face recognition with privacy preserved. It applies eigenface technique to reduce the dimension of face images for improving retrieval performance. With the assumption that the server is untrustworthy, PriFace uses the locality-sensitive hashing technique to introduce randomness into the face information for privacy preservation so that the server, or other adversaries, can not reconstruct any user’s face image. Experiments on real-world datasets demonstrate that the proposed PriFace can effectively preserve the privacy of face images and further outperforms the traditional methods. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Real-Time IoT-Enabled Biometric Attendance System

A Real-Time IoT-Enabled Biometric Attendance System

引用

International Conference on. Cryptology and Network security with Machine Learning, ICCNSML 2023

作者： Tripathi, Ashish Choudhary, Arjun Srivastava, Arun Kumar Kharbas, Vikash Kumar Shukla, Varun Department of CSE SCSE Galgotias University Greater Noida India Centre for Cyber Security Sardar Patel University of Police Security and Criminal Justice Jodhpur India Department of Computer Science and Engineering Lloyd Institute of Engineering & Technology Greater Noida India Department of Computer Science and Engineering Vivekananda Global University Jaipur India Kanpur India

ISBN: (纸本)9789819706402

Nowadays, biometric attendance system is applicable in various organizations to ensure the person's identity. The system takes parameters such as person's voice, fingerprint, retina, and face to authenticate the person. In order to track students’ daily attendance when they enroll in college, this article provides a biometric attendance system that uses blockchain technology. Both the daily and cumulative attendance of each student over the course of a chosen period of time, or month, is displayed by this system. The proposed system is designed to provide the cost-effective, systematic, and feasible solution to keep real-time attendance of the students against the existing manual system. Also, a webpage is designed for the same to provide a user-friendly and flexible platform to the students and faculty both to check the student's attendance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

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：