Abstract
The integration of Artificial Intelligence (AI) into diverse sectors has exponentially increased the generation, processing, and storage of sensitive data. Protecting this data against unauthorized access and ensuring its integrity and confidentiality is critical. Cryptographic solutions offer robust mechanisms to secure AI systems from various cyber threats while enabling privacy-preserving computation and data sharing. This article explores key cryptographic techniques such as homomorphic encryption, secure multi-party computation, and differential privacy, highlighting their role in safeguarding AI data pipelines. We also discuss the challenges in balancing cryptographic security with computational efficiency in AI applications, and future research directions.
All articles published in the American Journal of Cryptography and Network Security (AJCNS) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This license allows users to share (copy and redistribute) and adapt (remix, transform, and build upon) the material for any purpose, including commercial use, provided appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.