Notes on vector-store security, RAG poisoning, retrieval attacks, data exposure and the infrastructure underneath modern AI applications.
Retrieval Security10 min read
RAG security shouldn't start at the LLM. Why identity checks, tenant and classification filters, provenance and retention belong in the retrieval layer, before chunks ever reach the model.
Read →
Retrieval Security4 min read
Document permissions often disappear when content enters a vector store. Why RAG access controls, tenant isolation and least privilege need evidence, not assumptions.
Read →
RAG Poisoning6 min read
Indirect prompt injection and RAG poisoning turn the knowledge base itself into an attack surface. Why provenance and retrieval-layer visibility are security controls.
Read →
Data Privacy5 min read
Vector stores often hold original text, metadata and personal data. Why embeddings do not take a RAG system outside GDPR, CCPA and other data regulation.
Read →
