检索结果-内蒙古大学图书馆

28th International computer Science and engineering Conference, ICSEC 2024

作者： Piyawanno, Kittipon Nuntawisuttiwong, Taweechai King Mongkut's University of Technology Thonburi Department of Computer Engineering Bangkok Thailand

ISBN: (纸本)9798350366860

This research proposes a novel algorithm for password hashing, called the Sandwich Hashing algorithm, designed to protect credential information from channel interception as well as server-side data leakage. The algorithm comprises three main steps: credential information enrollment, credential information hashing at the client side, and credential information checking at the server side. Sandwich Hashing employs slow but secure hash functions like bcrypt or Argon2, combined with PBKDF2, to provide robust security against rainbow-Table and brute-force attacks. By using unique, random salts and timestamp buffers for each credential check, the algorithm enhances the protection of credential information from channel interception and server-side data leakage. Furthermore, hash values are partially stored on the server to resist such attacks. However, it is acknowledged that the algorithm remains vulnerable to parallel attacks involving simultaneous channel interception and server data leakage. This study details the algorithm's implementation, parameter settings, security capabilities, and limitations, demonstrating its superiority over traditional server-side and client-side hashing methods. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Delineating Indic Transliteration: Developing A Robust Model for Accurate Cross-Script Conversion

Delineating Indic Transliteration: Developing A Robust Model...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2024

作者： Shukla, Aditya Agrawal, Pragati Jain, Sweta Maulana Azad National Institute of Technology Department of Computer Science & Engineering Bhopal India

ISBN: (纸本)9798350348460

The aim of this study was to develop a reliable model of text change between two writing systems. ""(meaning "Hello") can be transliterated into Latin alphabet as "namaste". To achieve this goal, it use open data with multiple parallel reading samples in both languages. The dataset includes source language terms and their translations in the target writing process. This data set plays an important role in training the transliteration model, as it contains linguistic structures and variables that make the model flexible. The transliteration model was developed using a hybrid sequencing approach combined with deep learning models. This method trains an LSTM-based model on a dataset with carefully selected loss functions. Other conceptual techniques and developments can further help the model to capture the complex relationship between the source and target languages. To test our transliteration model, we created a custom test data set. This test data set contains only new samples, so that the accuracy of the samples can be assessed in terms of text texts that are not present in the training data. We measure the accuracy of the model's text conversion using carefully calculated metrics. And for testing purposes, I installed this on my local host as well. This study demonstrates that open-source data sets can be successfully used to develop transliteration models. The excellent performance of the model in the testing process highlights the ability to transfer information between two writing systems. This research advances the field by providing a framework for building script translation models using publicly available data, which can enhance natural language processing and facilitate cross-language communication in language and writing system. © 2024 IEEE.

关键词： Deep Learning Long-Short Term Memory Open-Source Dataset Padding Sequence Sequence2sequence Transliteration

来源：评论

学校读者我要写书评

暂无评论

The Eye: An AI-Powered Video Streaming Platform to Protect Children from Inappropriate Content 6

The Eye: An AI-Powered Video Streaming Platform to Protect C...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： El Bakri, Ahmad Yehia, Abdullah Ali, Mariam Osama, Reem Adel, Zeyad Gamal, Othman Saleh, Sherine Nagy Arab Academy for Science Technology and Maritime Transport Computer Engineering Department Alexandria Egypt

ISBN: (纸本)9798350378511

The Internet is now a vital part of our daily life including young children who watch their favorite cartoons using different streaming platforms. Unfortunately, these platforms often host content deemed inappropriate for children due to limited regulations. Manually reviewing the vast content is impossible, leaving parents with limited options to protect their children. Since parents in the Arabic culture have different beliefs on the content their children should be exposed to, and cannot rely on generic Kids' filters, accordingly 'The Eye' is proposed. The Eye is a streaming platform that allows children to watch videos while providing parents full flexibility to choose the exact content flags they deem inappropriate, ensuring their children enjoy a safe and age-suitable entertainment environment. The proposed model presents a hybrid CNN-RNN model to classify video content based on the predefined flags. A dataset was meticulously collected serving the different flags needed to train the proposed model and accordingly, the proposed trained model achieved an accuracy of approximately 67% on the test data. The model is deployed as a cloud-based service utilizing AWS infrastructure for efficient video processing and classification. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Tracking Waste Disposal and Generation of Fine to control and promote proper waste segregation

Tracking Waste Disposal and Generation of Fine to control an...

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Ashok, K.N. Kavyashree, K.S. Keerthana, S. Nagashree, C.R. Navya, L. S J C Institute of Technology Department of Computer Science and Engineering Chikkaballapur India

ISBN: (纸本)9798350359688

The metropolitan cities in India alone produce about 10 million tons of waste. That is, if left untreated, the waste materials will cause several types of pollution which are water, soil and air that destroy our ecosystem completely. People can avoid this madness by being waste conscious at an individual level. Lack of awareness and weak imposition of rules by authorities on separate household garbage pick-up are some reasons why many policies have failed to accomplish this. Thus, we aim to monitor and fine them whenever they don't obey the rules in segregating their household wastes. This project mainly deals with using web camera images to determine the percentage of non-segregating biodegradable from non-biodegradable waste during its collection by the municipal bodies for determining the fines based on improper disposal methods of waste products. One way of analysing the proportion of nonsegregated garbage is through Convolution Neural Networks (CNN), a deep learning algorithm. This groundbreaking solution advances responsible trash disposal methods that enhance a cleaner living environment for all people and future generations alike © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Efficient Security Solution for IoT and Cloud Security Using Lattice-Based Cryptography

An Efficient Security Solution for IoT and Cloud Security Us...

引用

2023 International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2023

作者： Bagla, Piyush Sharma, Ravi Mishra, Amit Kumar Tripathi, Neha Dumka, Ankur Pandey, Neeraj Kumar National Institute of Technology Department of Computer Science & Engineering Punjab Jalandhar India Graphic Era Hill University Department of Computer Science & Engineering Dehradun India Department of Computer Science & Engineering Dehradun India Women Institute of Technology Department of Computer Science & Engineering Dehradun India Dehradun India

ISBN: (纸本)9798350314878

This study introduces lattice-based cryptography to enhance security in IoT and cloud systems. It focuses on two fundamental challenges in lattice-based encryption. The paper compares the advantages and disadvantages of lattice-based encryption with traditional RSA and elliptic curve cryptography. Furthermore, it presents a novel approach called 'Lattice-based secure data aggregation,' specifically designed for IoT and cloud systems, ensuring confidentiality and integrity during data aggregation. The paper covers various aspects, such as data encryption, aggregation, decryption, and implementation on resource-constrained devices. Performance and security evaluations compare the proposed algorithm with other data aggregation techniques, demonstrating its effectiveness against attacks, computational efficiency, and low memory requirements. The paper also addresses the approach's limitations and proposes potential areas for future research. Overall, the proposed lattice-based cryptography offers a promising solution for privacy and security-sensitive IoT and cloud systems, making it a viable option for widespread adoption. © 2023 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Improving Network Security with Hybrid Model for DDoS Attack Detection 3

Improving Network Security with Hybrid Model for DDoS Attack...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Dandotiya, Monika Singh Makwana, Rajni Ranjan Madhav Institue of Technology & Science Department of Computer Science & Engineering MP Gwalior India

ISBN: (纸本)9798350354348

One of the most devastating forms of attack in the modern day is cyber-attacks. DDoS (Distributed Denial of Service) attacks are one kind of cyberattack. It is a kind of cyberattack in which the perpetrator takes over a network or a system and disables it, either temporarily or permanently, preventing its intended users from accessing it. Put simply, it's an attack where the target computer is bombarded with needless requests in an effort to overload it, crash it, and prevent people from accessing that network or machine. So, the most important thing to do to guard against DDoS attacks is to separate network data as soon as possible. In this study, we provide a new approach to intrusion detection algorithms known as CNN-GRU Attention. It combines Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), & a self-attention mechanism to improve algorithm accuracy. The model's structure is intended to effectively represent the geographical and temporal aspects of network flows. The experimental findings highlight the effectiveness of deep learning in cybersecurity applications, outperforming standard models. The experimental outcome showed that suggested hybrid model outperformed the competition on CICDDoS2019 data set, suggesting that it might be useful for detecting and categorising DDoS attack traffic. We evaluated the proposed system compared to state-of-the-art models. We are pleased to report that the accuracy of our work was 99.6%. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Congesting Ethereum after EIP-1559 6

Congesting Ethereum after EIP-1559

引用

6th IEEE International Conference on Blockchain and Cryptocurrency, ICBC 2024

作者： Arshi, Kianoush Goharshady, Amir Kafshdar Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350316742

We provide two novel block congestion attacks on Ethereum that are applicable even in the presence of the EIP-1559 base fee mechanism, which aimed to make such attacks impossible or highly costly. Unlike traditional block congestion methods, our approaches allow the attacker to avoid paying large transaction fees in case the attack is unsuccessful. Moreover, our second attack avoids an explosion in the block base fee and can thus be used for prolonged congestion of an interval of blocks. Finally, we provide real-world examples of contracts currently deployed on the Ethereum blockchain which are vulnerable to such attacks. Thus, block congestion is both possible and profitable, even after EIP-1559∗∗A longer version of this article, including a list of vulnerable contracts, is available at [1]. The research was partially supported by the Hong Kong Research Grants Council ECS Project 26208122. © 2024 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

High-Throughput Independent Component Analysis Processor for Full Duplex Systems

引用

IEEE Journal on Selected Areas in Communications 2023年第9期41卷 2821-2832页

作者： Cheng, Jen-Hao Chang, Tien-Min Shen, Chung-An Fouda, Mohammed E. Eltawil, Ahmed M. National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei10607 Taiwan University of California at Irvine Electrical Engineering and Computer Science Department IrvineCA92697 United States King Abdullah University of Science and Technology Electrical and Computer Engineering Program Thuwal23955 Saudi Arabia

This paper presents the algorithm and very-large-scale integration (VLSI) architecture of a high-throughput and highly efficient independent component analysis (ICA) processor for self-interference cancellation (SIC) in in-band full-duplex (IBFD) systems. This is the first VLSI architecture reported in the literature based on the state-of-the-art entropy bound minimization (EBM) approach. A novel ICA algorithm is presented in this paper with momentum gradient descent optimization. Simulation results show that the number of iterations for the proposed algorithm is significantly reduced compared to the conventional ICA algorithms. Furthermore, a novel early-distribution estimation scheme is proposed in the designed ICA processor to compute multiple distribution functions with low latency and low complexity. The processing flow and the efficiency for the hardware utilization are specifically designed so that the processing speed is maximized with minimum employment of hardware components. The proposed ICA processor is designed and implemented based on the application-specific-integrated circuit (ASIC) flow. The post-layout estimations show that compared with the conventional EBM-based scheme, the proposed design improves the throughput and efficiency by 30x. In addition, compared to prior designs shown in the literature, the proposed ICA processor also demonstrates a significant enhancement in terms of throughput and efficiency. © 1983-2012 IEEE.

关键词： VLSI circuits

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Machine Learning and Deep Learning Based Product Recommendation System 5th

A Comprehensive Analysis of Machine Learning and Deep Learni...

引用

5th EAI International Conference on Cognitive Computing and Cyber Physical Systems, IC4S 2024

作者： Chakravarthi, GKalyan Kumar, Raghvendra Addagarla, Ssvr Kumar Department of Computer Science and Engineering School of Engineering and Technology GIET University Odisha Gunupur India Nadimpalli Satyanarayana Raju Institute of Technology Visakhapatnam India

ISBN: (纸本)9783031770746

Recommender Systems (RS) have been widely applied in various real-time applications to support identifying valuable information. The RS tries to give actual suggestions to every user based on their behavior as well as interests. Recommendations generated by these systems often contend with the unique personal interests of individual users, thereby playing a pivotal role in their decision-making processes. Recommender Systems (RS) act as efficient tools for filtering vast amounts of online data, shaping the behaviors of smartphone users, personalization trends, and the evolution of internet access. RS are generally classified into three primary types: Hybrid Filtering, Content-Based Filtering (CBF), and Collaborative Filtering (CF). These systems find wide application across various fields including online education systems, e-commerce, marketing, tourism, food service, movies, business, and beyond. Although the recent RS are well-known in providing valuable recommendations, they suffer from a number of limitations as well as challenges such as scalability, sparsity, and cold-start and so on. Due to the various approach’s existence, the selection of these approaches becomes challenging during the development of application-based RS. Moreover, every approach comes with its individual feature sets, advantages as well as limitations, which must be addressed. This survey reviews the research inclinations which integrates the progressive technical characteristics of the RS. The aim of this survey is to ensure a systematic review on recent contributions in RS domain, and concentrated on various applications such as education, food, products and so on. This survey provides a comprehensive review of these types of RS, recent literature, and applications of visual RS. © ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Fake Review Detection and Classification Using Improved Convolutional Neural Network on Amazon Dataset 3

Fake Review Detection and Classification Using Improved Conv...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Sasikala, C. Ramya, S. RajeshKumar, S. Ramachandramoorthy, K.B. VijayaKumar, S. Umapathi, K. Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350322842

Fake reviews are a growing concern for e-commerce websites and other online platforms. To tackle this issue, researchers have developed an advanced convolutional neural network system that can detect and classify fake reviews. This system has been specifically designed to analyze the Amazon review dataset, and by integrating various text pre-processing methods and an innovative attention mechanism, it has significantly improved its classification accuracy. In fact, the proposed model outperforms existing state-of-the-art techniques in terms of accuracy and F1-score, with an impressive accuracy of 0.97. These results demonstrate the effectiveness of the improved CNN model in accurately detecting and classifying fake reviews, and provide a valuable tool for maintaining the authenticity and trustworthiness of online reviews. © 2023 IEEE.

关键词： Convolutional neural networks

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：