AI Model Safety and Security

Project: Basic Research

Project Details

Abstract

Project explores safety and security of generative AI models in the context of alignment, robustness and backdoor attacks

Submitting Institute Name

Hamad Bin Khalifa University (HBKU)
Sponsor's Award NumberQCRI-CORE-000015
Proposal IDQCRI-CORE-000015
StatusActive
Effective start/end date1/07/221/06/26

Primary Theme

  • Artificial Intelligence

Primary Subtheme

  • AI - Analytics & Decision Support

Secondary Theme

  • Artificial Intelligence

Secondary Subtheme

  • AI - Smart Society

Keywords

  • Safety and Security
  • Generative AI Models
  • None

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.