Download PDFOpen PDF in browser

Advanced Security for AI/ML Systems: Integrating Cloud Differential Privacy Strategies for Effective Risk Mitigation

EasyChair Preprint 14953

11 pagesDate: September 20, 2024

Abstract

As artificial intelligence (AI) and machine learning (ML) systems continue to proliferate across various sectors, ensuring the security and privacy of sensitive data has become paramount. This article explores advanced security measures tailored for AI/ML environments, focusing on the integration of cloud differential privacy strategies. We analyze the vulnerabilities inherent in AI/ML systems and discuss how differential privacy can mitigate risks associated with data exposure and model inversion attacks. By leveraging cloud computing resources, we propose a framework that enhances privacy without significantly compromising model performance or usability. Through empirical evaluations, we demonstrate the effectiveness of our approach in safeguarding data while maintaining the integrity and accuracy of AI/ML outputs. This work aims to contribute to the ongoing discourse on responsible AI practices and provide a pathway for organizations to implement robust security protocols in their AI/ML systems.

Keyphrases: AI/ML, Practices, Security, organization, robust, systems

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:14953,
  author    = {Anthony Collins},
  title     = {Advanced Security for AI/ML Systems: Integrating Cloud Differential Privacy Strategies for Effective Risk Mitigation},
  howpublished = {EasyChair Preprint 14953},
  year      = {EasyChair, 2024}}
Download PDFOpen PDF in browser