Business adoption of generative AI (GenAI) is surging, with teams like yours integrating GenAI with corporate documents, databases, and other internal repositories to address domain-specific problems and use cases. But with this accelerated deployment comes a heightened risk profile from several types of adversarial machine learning (AML) attacks, including theft, compromise, and escape of both ML data and models themselves.
Join us for an enlightening discussion, where we’ll explore prescriptive ways you can secure your GenAI systems against emerging, and rapidly evolving, AML dangers.
What you’ll learn:
- Specific AML tactics threat actors use to corrupt GenAI availability and operational integrity
- The risks associated with ML model tampering—and how to uphold your business's reputation
- Concrete strategies to thwart adversaries attempting to make unauthorized changes to your data and model sources
- The critical role of secure code signing processes in establishing authenticity and integrity throughout your AI system supply chain
