vector-database
Safeguard articles tagged "vector-database" — guides, analysis, and best practices for software supply chain and application security.
4 articles
Securing Vector Databases: The Overlooked Attack Surface in AI Apps
Vector databases became critical infrastructure the moment RAG went mainstream, but most are deployed with the security posture of a cache. Embeddings leak, indexes get poisoned, and tenants bleed into each other.
RAG Security Best Practices for 2026
Retrieval-augmented generation wired an untrusted-content pipeline straight into your model's context window. Here are the practices that keep a poisoned document or a leaked chunk from becoming an incident.
LLM Vector and Embedding Weaknesses
Embeddings aren't anonymized math — Vec2Text recovers 92% of text from vectors, and OWASP's LLM08:2025 now names inversion, poisoning, and exposed vector DBs as core AI risks.
RAG Poisoning: Defenses That Work
Retrieval-augmented generation is the most common LLM deployment pattern in the enterprise and the most commonly poisoned. A senior security engineer's playbook for defences that hold up in production.