RAG

Retrieval Augmented Generation (RAG) is a technique that enhances large language models by dynamically retrieving relevant external data to ground their responses in factual information. For AI governance, RAG systems present distinct compliance challenges around data source validation, retrieval accuracy, and transparency regarding which information influenced model outputs. Organizations must establish controls to ensure RAG systems cite authoritative sources, maintain audit trails of retrieved documents, and prevent the introduction of outdated or biased information into AI decision-making processes.

1 item

ResearchGlobal2026-09-09

GenAI Pen-Testing Guide Exposes Structural Gaps in Enterprise Red-Teaming Programs

CSO Online published a structured practitioner guide for penetration testing LLM, RAG, and GenAI applications, framing prompt injection as a campaign-level risk rather than a single-endpoint problem. The guide maps attack surfaces across retrieval pipelines, vector databases, tool integrations, and downstream APIs. It references the OWASP LLM guidance and the NIST 2025 adversarial machine-learning taxonomy as applicable compliance frameworks.

prompt injection LLM security RAG red teaming adversarial testing AI risk management OWASP