AI Data Security Guides

Guides to the ways enterprise AI systems expose data at the layer beneath the model. Most of that exposure runs through an AI knowledge base, meaning whatever corpus your AI retrieves from at query time, whether that's classic RAG over a vector store, agentic retrieval, GraphRAG or a set of connectors. The main guides define each failure mode in plain language, explain where it happens in a pipeline, and set out the controls and standards that apply, including how each one maps to MITRE ATLAS. Below them sit shorter pages answering one narrow question each. Written for security and data engineering teams, and kept current as the regulations move.

Start here
  • Understanding a failure mode. Start with the main guides below, then follow the deep dive that answers your specific question.
  • Testing your own system. Go straight to the RAG leakage self-test, which produces one number you can track over time.
  • Working a checklist. Use the RAG security checklist, and come back for the deep dive behind any line you cannot answer.
  • Mapping to a framework. The MITRE ATLAS guide lists the data-layer techniques, the crosswalk translates them into OWASP, NIST AI RMF, ISO/IEC 42001 and EU AI Act terms, and the posture assessment turns them into a repeatable coverage record.

AI Knowledge Base Security

Start here for the umbrella view. What counts as an AI knowledge base across classic RAG, agentic retrieval, GraphRAG, connector-based assistants and enterprise AI search, why retrieval is a security boundary rather than a product feature, the four ways a knowledge base leaks, and how to measure your own exposure before choosing controls.

The parent guide for the retrieval security cluster · NIST AI RMF and AI 600-1 · ISO/IEC 42001 · OWASP LLM01, LLM02 and LLM08

What Is Secure RAG? Securing Your AI Knowledge Base

Secure RAG means the retrieval pipeline enforces the entitlements and content controls of the data it serves. Covers the five pipeline stages, the four routes sensitive data leaks through retrieval, entitlement inheritance failures, indirect prompt injection, and where each control belongs. Applies to any AI knowledge base, not just classic RAG.

Includes a 7-question FAQ · OWASP LLM01, LLM02 and LLM08 · NIST AI 600-1 · EU AI Act Articles 10 and 12

Data Poisoning: How It Works and How to Prevent It

How poisoning differs from prompt injection, the four attack classes from NIST's adversarial ML taxonomy, the five lifecycle points where poisoned data enters, and how little an attacker actually needs. Includes the October 2025 finding that roughly 250 documents can backdoor a model regardless of size.

Includes a 6-question FAQ · NIST AI 100-2e2025 · EU AI Act Article 15 · OWASP LLM04

Training Data Leakage, Explained

Why models memorize, the five paths data takes on its way back out, and what extraction attacks actually recover in practice. Explains why holding sensitive fields back destroys the signal teams are training for, and what transformation does instead.

Includes a 7-question FAQ · Carlini and Nasr extraction research · EDPB Opinion 28/2024 · OWASP LLM02

AI Data Pipeline Security

The six stages of an AI data pipeline with the characteristic threat and control at each, why network allowlists and IAM are not positioned to stop data-layer attacks, and how the ML supply chain fits in. Uses the July 2026 Hugging Face intrusion as the worked example.

Includes a 7-question FAQ · CISA, NSA and FBI joint guidance · NIST SP 800-218A · MITRE ATLAS

MITRE ATLAS for AI Data Security

The MITRE ATLAS techniques that sit at the data layer, grouped by failure mode: retrieval leakage, indirect prompt injection, knowledge base and training data poisoning, extraction, and the data supply chain. What each one looks like in an enterprise deployment, the ATLAS mitigations that answer it, and why mapping findings to technique IDs is what makes an AI security posture assessment comparable over time.

Built against ATLAS 2026.08 · Companion pages: the five-framework crosswalk and the seven-step posture assessment

For a worked case study of a data-layer failure in production, see our analysis of the July 2026 Hugging Face breach, which entered through a dataset processing pipeline rather than through a model.

AI knowledge base security deep dives

Shorter pages under the Secure RAG guide, each answering one question about retrieval over sensitive data. Classic RAG, agentic retrieval, GraphRAG and connector-based assistants all inherit the same questions.

Framework mapping and posture assessment

Three pages for teams that need to report data-layer findings in the vocabulary of MITRE ATLAS, the OWASP Top 10 for LLM Applications, NIST AI RMF, ISO/IEC 42001 or the EU AI Act. Start with the ATLAS guide if you need to know what to test, the crosswalk if you need to translate a finding between frameworks, and the assessment procedure if you need a repeatable coverage record.

Run the test yourself

Secure RAG telemetry is the short, non-technical starting point. It covers what retrieval leakage is, what the open-source client measures, and how to get it running by pointing your own AI assistant at the repository.

The RAG leakage self-test procedure is a self-contained method for measuring whether your own retrieval path returns content a user should not see, using the open-source Hardshell telemetry client.