This lab will go into the basics of Retrieval Augmented Generation (RAG) through hands on access to a dedicated environment.

Protect AI Guardian is an ML model scanner and policy enforcer that ensures ML models meet an organization's security standards. It scans model code for malicious operators and vulnerabilities, while also checking against predefined policies. Guardian covers both first-party (developed within the organization) and third-party models (from external repositories). This comprehensive approach helps organizations manage ML model risks effectively. In this Lab, you will walk through the Protect AI Interface, explore the different feature sets there, and submit example models for scanning.

Explore the hidden dangers of prompt injection in Large Language Models (LLMs). This lab reveals how attackers manipulate LLMs to disclose private information and behave in ways that they were not intended to. Discover the intricacies of direct and indirect prompt injection and learn to implement effective guardrails.

The AI Security Enclave in the AI Proving Ground (AIPG) adds an environment dedicated to supporting AI security efforts and demonstrating WWT expertise and capabilities for testing innovative hardware and software security solutions.

Deep Instinct provides several solutions powered by deep learning to quickly identify potential attacks. This lab will demonstrate the capabilities of their Prevention for Storage solution, able to scan files in milliseconds anytime they enter the network or are edited. Files are scanned within the network environment, ensuring full data privacy, confidentiality, and compliance. Files that are found to be malicious can be either deleted or quarantined. Deep Instinct works with both network attached storages and cloud storages.