Loading
Topic
Prompt injection, data leakage, tool authorization, provenance, tenant isolation, and governance.
Practice items tagged with AI Security & Safety.
Builds a hybrid retrieval pipeline that enforces tenant scope before ranking, assembles a bounded context, and verifies returned citations.
Separates application instruction attacks from attempts to bypass a model's safety behavior and explains their overlapping defenses.
Handles a poisoned retrieval corpus by freezing ingestion, tracing provenance, switching immutable index versions, rebuilding clean data, and proving recovery.
Combines governed ingestion, authorized hybrid retrieval, reranking, grounded generation, citations, evaluation, observability, and fallback.
Combines threat modeling, injection containment, data minimization, tenant isolation, tools, audit, incident response, and governance.
Treats prompts as observable behavior, removes secrets and authorization policy from them, and limits the consequence of disclosure.