Scholarlink

<p>Digital Forensics (DFs) have played a significant role in investigating data breaches and other criminal activities. Most of the traditional works handled the data in a secure manner. None of them verified the access privileges that were altered by intruders, leading to security issues. Therefore, this paper proposes a DFA model using Gaussian Max-Norm Prior Regularization-based Quantum Bent Neural Network (GMNPR-QBNN) with strong cloud migration. Primarily, the server and user details are stored in the cloud server. Then, the QR code is generated from the extracted attributes of the DF data and registered details via user login. Afterward, the generated QR code and forensic data are stored in the IPFS via watermarking and data encryption. Meanwhile, the AP is created for the user and stored in the IPFS. Then, cloud server selection and migration using C2S-Fuzzy and AP verification are performed. After successful verification, the DFA starts by pre-processing the forensic data. Lastly, regarding the facial object features and point extraction, the classification is done to verify forensic data. Hence, the proposed GMNPR-QBNN attains 99.12% accuracy.</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

APV-based digital forensics analysis with cloud storage and migration using GMNPR-QBNN

  • 期刊论文

  • 发表日期：

    2026年3月17日

查看全文
  • B. Judy Flavai,
  • R. M. R. Shamija Sherryl,
  • S. Nalini Poornima,
  • Nikitha M. Kurian,
  • R. Vaishnavi,
  • S. Rubin Bose,
  • R. Swathi

摘要

Digital Forensics (DFs) have played a significant role in investigating data breaches and other criminal activities. Most of the traditional works handled the data in a secure manner. None of them verified the access privileges that were altered by intruders, leading to security issues. Therefore, this paper proposes a DFA model using Gaussian Max-Norm Prior Regularization-based Quantum Bent Neural Network (GMNPR-QBNN) with strong cloud migration. Primarily, the server and user details are stored in the cloud server. Then, the QR code is generated from the extracted attributes of the DF data and registered details via user login. Afterward, the generated QR code and forensic data are stored in the IPFS via watermarking and data encryption. Meanwhile, the AP is created for the user and stored in the IPFS. Then, cloud server selection and migration using C2S-Fuzzy and AP verification are performed. After successful verification, the DFA starts by pre-processing the forensic data. Lastly, regarding the facial object features and point extraction, the classification is done to verify forensic data. Hence, the proposed GMNPR-QBNN attains 99.12% accuracy.