Guardians of AI: Securing Generative AI Systems

This presentation will explore key questions around generative AI, including:
1. What generative AI systems are from a security practitioner perspective
2. Key security challenges specific to Generative AI: Data Privacy and Confidentiality, Adversarial Attacks, Model Bias and Fairness, Model Leakage and Intellectual Property
3. Best Practices for Secure Generative AI: Secure Model Deployment, Access Control and Authentication, Monitoring and Anomaly Detection, Regular Model Audits, Secure Data Handling, and Secure Training Pipelines
4. Case Studies: Deepfake Detection, Content Generation and Enhancing Security using generative AI
5. An Introduction to MITRE ATLAS™ (Adversarial Threat Landscape for Artificial-Intelligence Systems)