.png){kind=icon}
.png){kind=icon}
Return
Blockchain Data Encryption Method Based on Residual Network and AES
.png){kind=icon}
PRE
AI
DOI：10.1002/spy2.70196.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In response to the problems of insufficient encryption performance, low security, complex key management, and lack of flexibility in traditional blockchain encryption technology, the study proposes a blockchain data encryption model based on residual network and advanced encryption standard (AES). The model adopts convolutional block attention module (CBAM) to optimize the feature extraction ability of the residual network, thereby improving the adaptability to diverse data structures and reliability of the model. At the same time, the model combines the powerful confidentiality, encryption integrity, and encryption efficiency of AES to improve the encryption efficiency and security of the encryption model. Experimental data showed that the model achieved approximately 98% encryption integrity in both different datasets. After 250 rounds of training, its encryption accuracy increased to about 98.5%, and its decryption accuracy approached 99%. When the sample size increased to 60, the encryption delay was only 45 ms. At the same time, the running delay of the model was relatively low, and the CPU usage was often below 40%. The results indicate that the designed encryption model has stronger adaptability and operational performance, and can provide a more secure and efficient encryption scheme for IoT blockchain systems. This model is suitable for real-time protection of financial transactions and social media privacy data. It is of great significance in promoting the application of blockchain technology in fields such as finance and healthcare.
Keywords:
AES
blockchain
CBAM
data encryption
residual networks
Journal
S
IF:
2.1
Papers:
125
Citations:
717