Rate the Article: Securing Meta-Learning: Methods and Applications, IJSR, Call for Papers, Online Journal
International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064

Downloads: 2 | Views: 231 | Weekly Hits: ⮙1 | Monthly Hits: ⮙2

Analysis Study Research Paper | Computer and Mathematical Sciences | United States of America | Volume 13 Issue 7, July 2024 | Rating: 5 / 10


Securing Meta-Learning: Methods and Applications

Virender Dhiman


Abstract: Meta-learning frameworks must be secured due to data sensitivity and adversaries. The three main security methods are homomorphic encryption (HE), differential privacy (DP), and Federated Learning (FL). Each approach is tested for accuracy, attack resistance, computing efficiency, and scalability. HE offers data confidentiality with encrypted computations but substantial processing expense. By injecting noise, DP balances privacy and accuracy. FL improves privacy and scalability through decentralized learning, but communication cost and non-IID data issues remain. Application needs determine method: HE for high secrecy, DP for robust privacy, FL for decentralized applications. HE, DP, and FL hybrid models should be studied to increase computational efficiency and manage non-IID data in secure meta-learning applications in healthcare, banking, and IoT networks.


Keywords: Meta-learning security, Homomorphic Encryption, Differential Privacy, Federated Learning, Adversarial threats, Computational efficiency, Non-IID data


Edition: Volume 13 Issue 7, July 2024,


Pages: 55 - 62



Rate this Article


Select Rating (Lowest: 1, Highest: 10)

5

Your Comments (Only high quality comments will be accepted.)

Characters: 0

Your Full Name:


Your Valid Email Address:


Type This Verification Code Below: 8473


Top