A security-enhanced and privacy-preserving certificateless aggregate signcryption scheme based artificial neural network in wireless medical sensor network

• Published in: IEEE sensors journal 2023-04, Vol.23 (7), p.1-1
• Main Authors: Ren, Runtao, Su, Jinqi
• Format: Article
• Language: English
• Subjects: Aggregates; Algorithms; Artificial neural networks; Certificateless signcryption; Complexity; Cryptography; Curves; Cybersecurity; Deep learning; Deep neural network; Digital signatures; Encryption; Neural networks; Nodes; Privacy; Privacy preserving; Random oracle model; Read only memory; Security; Sensors; Wireless network; Wireless networks; Wireless sensor networks
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2023.3247581

With the recent advances in mobile sensing and beyond-5G technologies, wireless medical sensor networks (WMSN) have become an emerging hot topic in smart healthcare. Under the condition of limited resources of medical sensor nodes, ensuring the accuracy and integrity of a large number of patients' medical data is a crux for security and data privacy issues. In order to overcome the limitations of medical sensors in communication and computing capabilities, and to achieve privacy in WMSN, we propose a low complexity certificateless aggregate signcryption (CL-ASC) scheme based artificial neural network for safely achieving authentication and unforgeability of medical nodes. We use adaptive sigma filter for denoising, adopt Levenshtein entropy for encoding and design cryptographic protocol for signcrypting in the hidden layer of deep feedforward artificial neural network. The CL-ASC can authenticate all sensing bioinformation at once in a privacy-preserving way. Given the challenge of applying a discrete logarithm and computational Diffie-Hellman problems based on elliptic curve, the proposed scheme satisfies the IND-CCA and the UF-CMA security properties under the random oracle model. Finally, the benchmark evaluation shows that ours is ahead of similar state-of-the-art schemes, due to its low complexity and higher computational efficiency. Researchers interested in the provable security protocol design and framework of neural networks can gain useful insights from this research and identify future cross-domain of cyber security and neural networks research directions based on the proposed scheme herein.