检索结果-内蒙古大学图书馆

33rd Companion of the ACM World Wide Web Conference, WWW 2023

作者： Kuo, Kuan-Hung Wang, Ming-Hung Kao, Hung-Yu Dai, Yu-Chen National Chung Cheng University Department of Computer Science and Information Engineering Chiayi Taiwan National Institute of Cyber Security Taipei Taiwan

ISBN: (纸本)9798400701726

The evolution of political campaigns is evident with the ascent of social media. Ideological beliefs are increasingly disseminated through political-affiliated fan pages. The interaction between politicians and the general public on these platforms plays a pivotal role in election outcomes. In this study, we utilize a multimodal approach to explore and quantify similarities of ideologies among political fan pages. we employed visualization techniques to demonstrate the political stance of each fan page. To validate our proposal, we concentrated on an analysis of the 2021 national referendums in Taiwan, encompassing a collection of fan pages and their corresponding posts that were related to these referendums. Through a qualitative analysis of the content of these fan pages, the efficacy of our multimodal framework in clustering fan pages according to their respective political ideologies was evaluated. The findings of this study underscore the significant enhancement in the accuracy of stance detection when integrating multiple modalities of data, namely textual content, visual imagery, and user interactions. © 2024 Copyright held by the owner/author(s).

关键词： Image enhancement

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

A MULTIMODAL FRAMEWORK FOR SATIRE VS. SARCASM DETECTION 15

A MULTIMODAL FRAMEWORK FOR SATIRE VS. SARCASM DETECTION

引用

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

作者： Goyal, Devansh Mishra, Santosh Kumar Rai, Vikash Kumar Department of Computer Science and Engineering RGIPT Jais Amethi India School of Cyber Security and Digital Forensics NFSU Goa Goa India

ISBN: (纸本)9798350370249

Sarcasm and satire are common ways to communicate complicated ideas with humor and irony, both expressing criticism or mockery. Detecting sarcasm vs. satire in real life can foster better communication by understanding intent, preventing misunderstandings, and promoting critical thinking and empathy. We introduce an innovative dataset for detecting Multi-modal Satire vs. Sarcasm, leveraging the MUStARD dataset for its construction. This dataset includes visual utterances annotated with sarcasm and satire labels, enriching its potential for studying multimodal satire and sarcasm detection. This enriched dataset serves as a robust foundation for training and evaluating machine learning and deep learning architectures that combine textual and visual cues to identify satire and sarcasm in multimedia content. By incorporating this enhanced dataset, the research aims to advance the field of multimodal satire and sarcasm detection and contribute to a deeper understanding of humor and irony in online communication. We carry out experimentation with various architectures like LSTM, GPT2, BERT, SVM, and Logistic Regression. The proposed architecture achieves an F1 score of 0.956, outperforming other baselines. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in physiological characteristics recognition for internet of things authentication

引用

Digital Communications and Networks 2024年第3期10卷 740-755页

作者： Zhimin Zhang Huansheng Ning Fadi Farha Jianguo Ding Kim-Kwang Raymond Choo School of Computer and Communication Engineering University of Science and Technology BeijingBeijing100083China Beijing Engineering Research Center for Cyberspace Data Analysis and Applications Beijing100083China Faculty of Informatics Engineering Aleppo UniversityAleppoSyria Department of Computer Science Blekinge Institute of Technology37179KarlskronaSweden Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Effective user authentication is key to ensuring equipment security,data privacy,and personalized services in Internet of Things(IoT)***,conventional mode-based authentication methods(e.g.,passwords and smart cards)may be vulnerable to a broad range of attacks(e.g.,eavesdropping and side-channel attacks).Hence,there have been attempts to design biometric-based authentication solutions,which rely on physiological and behavioral *** characteristics need continuous monitoring and specific environmental settings,which can be challenging to implement in ***,we can also leverage Artificial Intelligence(AI)in the extraction and classification of physiological characteristics from IoT devices processing to facilitate ***,we review the literature on the use of AI in physiological characteristics recognition pub-lished after *** use the three-layer architecture of the IoT(i.e.,sensing layer,feature layer,and algorithm layer)to guide the discussion of existing approaches and their *** also identify a number of future research opportunities,which will hopefully guide the design of next generation solutions.

关键词： Physiological characteristics recognition Artificial intelligence Internet of things Biological-driven authentication

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

IDCE:Integrated Data Compression and Encryption for Enhanced security and Efficiency

引用

computer Modeling in engineering & sciences 2025年第4期143卷 1029-1048页

作者： Muhammad Usama Arshad Aziz Suliman A.Alsuhibany Imtiaz Hassan Farrukh Yuldashev Department of Cyber Security Pakistan Navy Engineering CollegeNational University of Sciences and TechnologyKarachi75350Pakistan Department of Computer Science Main CampusIqra UniversityKarachi75500Pakistan Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Informatics and Its Teaching Methods Tashkent State Pedagogical UniversityTashkent100170Uzbekistan

Data compression plays a vital role in datamanagement and information theory by reducing ***,it lacks built-in security features such as secret keys or password-based access control,leaving sensitive data vulnerable to unauthorized access and *** the exponential growth of digital data,robust security measures are *** encryption,a widely used approach,ensures data confidentiality by making it unreadable and unalterable through secret key *** their individual benefits,both require significant computational ***,performing them separately for the same data increases complexity and processing *** the need for integrated approaches that balance compression ratios and security levels,this research proposes an integrated data compression and encryption algorithm,named IDCE,for enhanced security and *** on 128-bit block sizes and a 256-bit secret key *** combines Huffman coding for compression and a Tent map for ***,an iterative Arnold cat map further enhances cryptographic confusion *** analysis validates the effectiveness of the proposed algorithm,showcasing competitive performance in terms of compression ratio,security,and overall efficiency when compared to prior algorithms in the field.

关键词： Chaotic maps security data compression data encryption integrated compression and encryption

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Detection and Recognition using CNN and KERAS

Traffic Sign Detection and Recognition using CNN and KERAS

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： Digvijay Prabhat J. Pardhiv Sai S Vishnupriya S. S. Subashka Ramesh Computer Science and Engineering with Specialization in Cyber Security SRM IST Ramapuram Chennai India Department of Computer Science and Engineering SRM IST Ramapuram Chennai India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

A traffic sign detection and recognition system based on CNN with high-accuracy and possibility of real-time implementation for autonomous driving applications has been presented. The Keras framework was used to develop the system, which overcomes limitations of traditional traffic sign recognition methods, commonly found to fail due to environmental variations such as changing light, object occlusions, or damaged traffic signs. It takes advantage of the comprehensive GTSRB dataset and performs data augmentations so as to generalize well to different driving environments. The optimized convolutional and pooling layers in the CNN architecture allow for efficient extraction of salient features, which is crucial as ASL often has similar sign classes that need to be differentiated across variations in scale, illumination, and orientation. The system ensures sign recognition instantaneously and with accurate classification performance, improving safety and efficiency of autonomous driving by providing a fast-accurate real-time recognition of a sign.

关键词： Accuracy Lighting Manuals Feature extraction Data augmentation Real-time systems Data models Safety Convolutional neural networks Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Smart Music Recommendation System Integrating NLP and Hybrid Algorithms

Smart Music Recommendation System Integrating NLP and Hybrid...

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： S. Roshan Kumar S. S. Subashka Ramesh Harsha Vardan V Adithya Yuvan Computer Science and Engineering with Specialization in Cyber Security SRM IST Ramapuram Chennai India Department of Computer Science and Engineering SRM IST Ramapuram Chennai India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

In an era where technological growth gives a massive amount of knowledge in music, intuitive and personalized music delivery forms the cornerstone for better user experience and satisfaction. The increasing reliance on voice-driven interfaces can be leveraged to create newer music recommendation systems. This paper explores the development of the Smart Music Recommendation System, which will use natural language processing (NLP), speech recognition, and hybrid algorithms to recommend music to the user based on his mood input through voice. The system leverages Google Speech Recognition API for real-time voice interaction ensuring a seamless interaction between the user and the system. The system additionally detects the user’s emotional state from voice commands, while search algorithms are employed to fetch and recommend songs. A hybrid recommendation approach combines content-based filtering for emotion-specific playlist generation for every mood for an enhanced listening experience. An exceptional feature in our system is offline download using Yt-dlp to any local device and playback processes using an automated threading mechanism. The system proposed here was tested and gave efficient performance in voice interaction, song suggestion according to mood, and coordination with external platforms for retrieving and playing songs.

关键词： Sentiment analysis Accuracy Mood Filtering Multimedia systems Speech recognition Real-time systems Internet Web sites Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Novel method for ranking batsmen in Indian Premier League

引用

Data science and Management 2023年第3期6卷 158-173页

作者： M.K.Manju Abin Oommen Philip Department of Computer Science&Engineering Toch Institute of Science&TechnologyErnakulamKerala682313India Department of CSE-Cyber Security Indian Institute of Information TechnologyKottayam686635India

Sports analytics have benefited immensely from the growth and popularity of artificial intelligence and machine *** techniques enable sports analysts to evaluate player performance more effectively.A literature review of player performance evaluation methods shows the need to develop a new performance evaluation index for Twenty20(T20)cricket.A novel framework was proposed to evaluate batsman strength based on individual performance,role in the team,and team ***,proposed ranking systems are derived from static networks,that is,the aggregation of game results over ***,the scores of the players(or teams)fluctuate over ***,defeating a renowned player during peak performance is more rewarding than defeating the same player during other *** account for this,we propose a new method and apply it to the T20 format Indian Premier *** method serves three main purposes:First,it creates a new performance index for players to rank them more accurately and ***,the players are clustered based on their *** the third phase,a social network analysis approach is applied to visualize and analyze crickets as a network to gain better insights into players’team *** novel approach is a helpful index for sports coaches,analysts,cricket fans,and managers to evaluate player performance and rank for future aspects.

关键词： Indian Premier League Social network analysis Artificial intelligence Machine learning

来源：评论

学校读者我要写书评

暂无评论

Efficient Publication of Distributed and Overlapping Graph Data Under Differential Privacy

引用

Tsinghua science and Technology 2022年第2期27卷 235-243页

作者： Xu Zheng Lizong Zhang Kaiyang Li Xi Zeng the School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China China Electronics Technology Cyber Security Co.Ltd. Chengdu 610000China

Graph data publication has been considered as an important step for data analysis and *** data,which provide knowledge on interactions among entities,can be locally generated and held by distributed data *** data are usually sensitive and private,because they may be related to owners’personal activities and can be hijacked by adversaries to conduct inference *** solutions either consider private graph data as centralized contents or disregard the overlapping of graphs in distributed ***,this work proposes a novel framework for distributed graph *** this framework,differential privacy is applied to justify the safety of the published *** includes four phases,i.e.,graph combination,plan construction sharing,data perturbation,and graph *** published graph selection is guided by one data coordinator,and each graph is perturbed carefully with the Laplace *** problem of graph selection is formulated and proven to be ***,a heuristic algorithm is proposed for *** correctness of the combined graph and the differential privacy on all edges are *** study also discusses a scenario without a data coordinator and proposes some insights into graph publication.

关键词： graph data distributed data publication differential privacy

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：