References: Security, Privacy, and Vector Search

1. Zero Trust Security - Wikipedia - Defines the zero-trust security model including never-trust-always-verify principles, continuous authorization re-evaluation, and least-privilege access — directly foundational for this chapter's zero-trust graph architecture section showing how implicit trust assumptions must be eliminated from context graph deployments.

2. Attribute-Based Access Control - Wikipedia - Covers ABAC policy models including subject, resource, action, and environment attributes evaluated at access time — directly supporting this chapter's ABAC section showing how fine-grained access policies for context graph nodes and edges require multi-attribute evaluation beyond what role-based access control can express.

3. Approximate Nearest Neighbor Search - Wikipedia - Explains nearest neighbor search algorithms including exact and approximate methods, trade-offs between recall and latency, and the curse of dimensionality — directly foundational for this chapter's ANN section comparing HNSW, LSH, and IVF-PQ for different context graph collection sizes and latency requirements.

4. Hands-On Large Language Models - Jay Alammar, Maarten Grootendorst - O'Reilly Media - Chapter 9 covers embedding models, sentence transformers, dense retrieval, and vector search for semantic similarity — directly supporting this chapter's sections on embedding models, sentence transformers, dense retrieval, and the hybrid retrieval pipeline combining ANN search with graph traversal.

5. Artificial Intelligence: A Modern Approach (4th ed.) - Stuart Russell, Peter Norvig - Pearson - Chapter 28 covers AI safety, privacy-preserving AI, and responsible AI deployment including federated learning, access control for AI systems, and model auditing — directly relevant to this chapter's federated learning, model audit trail, and zero-trust AI agent permission sections.

6. Federated Learning - Wikipedia - Explains federated learning mechanics including local model training, gradient aggregation, and privacy-preserving techniques — directly supporting this chapter's federated learning section covering cross-organization retrieval model training and jurisdiction-compliant cross-border model improvement for multi-organization context graph deployments.

7. Vector Database - Wikipedia - Covers vector database architectures including embedding storage, ANN indexing, and hybrid search integration — foundational for this chapter's vector database section explaining how vector databases complement graph databases in a complete context graph retrieval stack.

8. Sentence Transformers - SBERT.net - The official documentation for sentence transformers including model architectures, fine-tuning methodology, and pre-trained models for semantic similarity tasks — directly supporting this chapter's sentence transformer section covering domain-specific fine-tuning for context graph retrieval and the virtuous cycle between user feedback and model improvement.

9. Information Security - Wikipedia - Covers information security principles including access control, data classification, audit logging, and cryptographic integrity verification — supporting this chapter's graph security model section defining the four pillars of authentication, authorization, data classification, and audit logging for context graph deployments.

10. Return on Investment - Wikipedia - Explains ROI calculation methodologies including cost modeling, benefit quantification, and time-series projection — directly supporting this chapter's context graph ROI model covering infrastructure, implementation, and operational costs against decision speed, quality, onboarding, and compliance benefit dimensions.