Agricultural data privacy and federated learning: A review of challenges and opportunities
University of Messina · SingularLogic (Greece) · +2 more institutions
Abstract
• Comprehensive review of Federated Learning (FL) in agriculture: This study examines the potential of FL in addressing critical agricultural data privacy concerns without compromising data-driven decision-making. • Privacy-preserving techniques explored: The review evaluates core privacy-enhancing methods like Homomorphic Encryption (HE), Secure Multi-Party Computation (SMPC), and Differential Privacy (DP) applied to agricultural data. • Applications in agriculture: Federated Learning (FL) role in key areas such as crop disease detection, yield prediction, and resource optimization are highlighted, emphasizing its ability to retain data confidentiality. • Challenges in rural adoption: The review identifies…
Citation impact
- FWCI
- 128.61
- Percentile
- 100%
- References
- 109
Authors
6Topics & keywords
- Agriculture
- Internet privacy
- Information privacy
- Computer science
- Data science
- Computer security
- Business
- Geography
- Zero hunger