Scholarlink

<p>Protecting confidential financial in sequence has become a top precedence for companies in the financial production in the current digital age. The internet can be used to access cloud property without the requirement for specialized infrastructure. The security of cloud apps are being efficiently managed via cloud computing (CC). A machine learning (ML) technique called data categorization determines the estimated class of unstructured material. Using advanced cryptographic techniques like multi-objective spatial support vector machine (MOSSVM) for our suggested system since it can handle difficult and nonlinear constraints. This technique may maximize several objectives; it is suited for use in areas with better security and proper data classification, such as financial industries. Algorithms and elliptic curve cryptography (ECC) encryption, the goal of this project is to categorize financial data using an enhanced MOSSVM and protect it with ECC encryption study proposes a comprehensive advance for categorizing and defending data in the financial sector. Using MOSSVM, sensitive and non-sensitive data are distinguished, and the sensitive data is efficiently encrypted using the ECC technique. Through multi-factor authentication, the proposed approach aims tSo support cloud security while offering accurate and efficient classification of data. In order to assess encryption and decryption times, the study contrasts the suggested encryption technique, ECC, with previous ones, like TripleDES, SDES-HC, and the SHA3 hashing algorithm. We evaluate accuracy, precision, recall, and f1-score using established methods and the proposed method MOSSVM It scores 99.3% accuracy, 99.4% precision, 99.55% recall, and an F1-score of 99.65%. These findings demonstrate MOSSVM’s effectiveness in providing high security and accurate data categorization for financial industry applications. Overall, a thorough approach to categorize and protective information in the economic sector is provided by the suggested MOSSVM-based cloud security solution with ECC encryption.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning-based cloud security system with multi authentication for data classification in Financial Sectors

  • 期刊论文

  • 发表日期：

    2025年1月8日

查看全文
  • P. V. Chandrika,
  • Sandeep Kelkar,
  • Bijith Marakarkandy,
  • S. S. Prasada Rao

摘要

Protecting confidential financial in sequence has become a top precedence for companies in the financial production in the current digital age. The internet can be used to access cloud property without the requirement for specialized infrastructure. The security of cloud apps are being efficiently managed via cloud computing (CC). A machine learning (ML) technique called data categorization determines the estimated class of unstructured material. Using advanced cryptographic techniques like multi-objective spatial support vector machine (MOSSVM) for our suggested system since it can handle difficult and nonlinear constraints. This technique may maximize several objectives; it is suited for use in areas with better security and proper data classification, such as financial industries. Algorithms and elliptic curve cryptography (ECC) encryption, the goal of this project is to categorize financial data using an enhanced MOSSVM and protect it with ECC encryption study proposes a comprehensive advance for categorizing and defending data in the financial sector. Using MOSSVM, sensitive and non-sensitive data are distinguished, and the sensitive data is efficiently encrypted using the ECC technique. Through multi-factor authentication, the proposed approach aims tSo support cloud security while offering accurate and efficient classification of data. In order to assess encryption and decryption times, the study contrasts the suggested encryption technique, ECC, with previous ones, like TripleDES, SDES-HC, and the SHA3 hashing algorithm. We evaluate accuracy, precision, recall, and f1-score using established methods and the proposed method MOSSVM It scores 99.3% accuracy, 99.4% precision, 99.55% recall, and an F1-score of 99.65%. These findings demonstrate MOSSVM’s effectiveness in providing high security and accurate data categorization for financial industry applications. Overall, a thorough approach to categorize and protective information in the economic sector is provided by the suggested MOSSVM-based cloud security solution with ECC encryption.