Efficient medical image encryption and attack detection using hyperchaotic fibonacci polynomial convolutional neural network in IoT healthcare networks

Due to the fast expansion of IoT technology in the health-related field, secure transfer of sensitive medical data in general, and of medical images in particular, has become a major concern. Conventional detection and encryption techniques usually cannot guarantee both high security and computation...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Neurocomputing (Amsterdam) Ročník 656; s. 131537
Hlavní autori:	Veerasekharreddy, Bhumireddypalli, Chinniah, P., Rao, P. Varaprasada, Arunachalam, Krishna Prakash
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 01.12.2025
Predmet:	Crayfish optimization algorithm Fibonacci Q matrix encryption Hierarchical auto-associative polynomial convolutional neural network Crayfish optimization algorithm Fibonacci Q matrix encryption Hierarchical auto-associative polynomial convolutional neural network
ISSN:	0925-2312
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	Due to the fast expansion of IoT technology in the health-related field, secure transfer of sensitive medical data in general, and of medical images in particular, has become a major concern. Conventional detection and encryption techniques usually cannot guarantee both high security and computational efficiency under strict real-time constraints. To counter the above problems, this research proposed a novel Hyperchaotic Fibonacci Polynomial Convolutional Neural Network with Crayfish Optimization Algorithm (HFPCNN-COA) for increased medical image security in IoT environments. The medical images are first encrypted with Hyperchaotic System-Fibonacci Q Matrix Encryption (HFQE) on a standard collection. After encryption, they are sent over the network. After transmission, the HAPCNN is applied to detect and classify any potential tampering or transmission attacks. The loss function of HAPCNN is optimized with the Crayfish Optimization Algorithm (COA) to increase the detection accuracy and convergence speed. Lastly, cryptanalysis is conducted to measure the system's resilience to attack. The experimental results prove the workability of the proposed framework, with a Peak Signal-to-Noise Ratio (PSNR) of 53 dB, which corresponds to very good retention of image quality. In addition, the proposed method is quite resistant to data manipulation with a 0.4 % Bit Error Rate (BER) and has reasonable processing times with encryption times of 2.87 ms and decryption times of 2.35 ms. This shows that HFPCNN-COA holds a great deal of promise as an actual and secure means for the transfer of medical image data for IoT-based healthcare systems.
ISSN:	0925-2312
DOI:	10.1016/j.neucom.2025.131537