安全面部验证:利用 ResNet50-DenseNet 检测欺骗攻击的混合模型121

Aya ElSayed, Noha A. Hikal, Nehal A. Sakr, Ali E. Takieldeen
{"title":"安全面部验证:利用 ResNet50-DenseNet 检测欺骗攻击的混合模型121","authors":"Aya ElSayed, Noha A. Hikal, Nehal A. Sakr, Ali E. Takieldeen","doi":"10.21608/ijt.2024.293947.1055","DOIUrl":null,"url":null,"abstract":": The present study introduces a novel hybrid deep learning model, leveraging the synergies inherent in the amalgamation of ResNet50 and DenseNet121 architectures. This fusion aims to effectively tackle the formidable task of detecting spoof attacks. Spoof attacks pose a significant threat to digital systems and networks, where adversaries attempt to deceive systems by impersonating legitimate users or sources. The proposed hybrid model aims to enhance detection accuracy and robustness against various spoof attacks by leveraging the complementary features of ResNet50 and DenseNet121. Integrating these architectures creates a unified framework that effectively captures local and global input data features, enabling more comprehensive detection capabilities. The problem of detecting spoofing attacks is stated as a classification task, and we train the hybrid model using large-scale datasets comprising fake and real data samples. The experimental results illustrate the superior performance of the proposed hybrid model in comparison to individual SVM, KNN, CNN, and RNN models, highlighting its efficacy in mitigating the risks associated with spoof attacks in digital systems and networks.","PeriodicalId":517010,"journal":{"name":"International Journal of Telecommunications","volume":"21 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Secure Facial Verification: A hybrid model for detecting Spoof Attacks with ResNet50-DenseNet121\",\"authors\":\"Aya ElSayed, Noha A. Hikal, Nehal A. Sakr, Ali E. Takieldeen\",\"doi\":\"10.21608/ijt.2024.293947.1055\",\"DOIUrl\":null,\"url\":null,\"abstract\":\": The present study introduces a novel hybrid deep learning model, leveraging the synergies inherent in the amalgamation of ResNet50 and DenseNet121 architectures. This fusion aims to effectively tackle the formidable task of detecting spoof attacks. Spoof attacks pose a significant threat to digital systems and networks, where adversaries attempt to deceive systems by impersonating legitimate users or sources. The proposed hybrid model aims to enhance detection accuracy and robustness against various spoof attacks by leveraging the complementary features of ResNet50 and DenseNet121. Integrating these architectures creates a unified framework that effectively captures local and global input data features, enabling more comprehensive detection capabilities. The problem of detecting spoofing attacks is stated as a classification task, and we train the hybrid model using large-scale datasets comprising fake and real data samples. The experimental results illustrate the superior performance of the proposed hybrid model in comparison to individual SVM, KNN, CNN, and RNN models, highlighting its efficacy in mitigating the risks associated with spoof attacks in digital systems and networks.\",\"PeriodicalId\":517010,\"journal\":{\"name\":\"International Journal of Telecommunications\",\"volume\":\"21 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Telecommunications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.21608/ijt.2024.293947.1055\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Telecommunications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21608/ijt.2024.293947.1055","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

:本研究介绍了一种新型混合深度学习模型,利用了 ResNet50 和 DenseNet121 架构融合所固有的协同效应。这种融合旨在有效解决检测欺骗攻击这一艰巨任务。欺骗攻击对数字系统和网络构成重大威胁,对手试图通过冒充合法用户或来源来欺骗系统。所提出的混合模型旨在利用 ResNet50 和 DenseNet121 的互补特性,提高针对各种欺骗攻击的检测准确性和鲁棒性。整合这些架构可创建一个统一的框架,有效捕捉本地和全局输入数据特征,从而实现更全面的检测能力。检测欺骗攻击的问题被表述为一项分类任务,我们使用由虚假和真实数据样本组成的大规模数据集来训练混合模型。实验结果表明,与单独的 SVM、KNN、CNN 和 RNN 模型相比,所提出的混合模型具有更优越的性能,突出了它在降低数字系统和网络中与欺骗攻击相关的风险方面的功效。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Secure Facial Verification: A hybrid model for detecting Spoof Attacks with ResNet50-DenseNet121
: The present study introduces a novel hybrid deep learning model, leveraging the synergies inherent in the amalgamation of ResNet50 and DenseNet121 architectures. This fusion aims to effectively tackle the formidable task of detecting spoof attacks. Spoof attacks pose a significant threat to digital systems and networks, where adversaries attempt to deceive systems by impersonating legitimate users or sources. The proposed hybrid model aims to enhance detection accuracy and robustness against various spoof attacks by leveraging the complementary features of ResNet50 and DenseNet121. Integrating these architectures creates a unified framework that effectively captures local and global input data features, enabling more comprehensive detection capabilities. The problem of detecting spoofing attacks is stated as a classification task, and we train the hybrid model using large-scale datasets comprising fake and real data samples. The experimental results illustrate the superior performance of the proposed hybrid model in comparison to individual SVM, KNN, CNN, and RNN models, highlighting its efficacy in mitigating the risks associated with spoof attacks in digital systems and networks.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信