Editorial desk
AI Defense Editorial
AI Defense Editorial is the publishing identity for AI Defense. It is a desk, not a person: no named author, no biography, no professional certifications.
Articles published under this byline are researched from primary sources — vendor and project documentation, published standards and specifications, research papers, and measurements published by whoever took them — drafted with AI assistance, and edited against those cited sources before publication. Nothing here is based on first-hand testing in a private lab, and any figure that appears is attributed to the source it came from.
Corrections go to hello@aidefense.dev. More detail is on the about page and the editorial disclosure.
Posts (19)
- Threats
Indirect Prompt Injection Explained: Defenses That Hold
How indirect prompt injection works, why LLMs cannot separate instructions from data, and the layered defenses Microsoft and Google use.
- Guardrails
LLM Guardrail Benchmarks: Build Your Own Eval Set
Why published guardrail benchmarks do not transfer, and how to build a held-out eval set with hard negatives, attack success rate, and a latency budget.
- Monitoring
LLM Audit Logging: What to Log, Redact, and Retain
A field-level guide to LLM audit logging: which attributes to persist, what to redact before storage, retention tiers, and the compliance floor.
- Detection
Jailbreak Detection for LLMs Explained: How Runtime Filters Work
A plain-language breakdown of jailbreak detection for LLMs: how perplexity heuristics and classifiers work, where they sit, and where they fail.
- Guardrails
Best LLM Guardrail Frameworks for 2026: A Data-Driven Comparison
Comparing the best LLM guardrail frameworks for 2026: NeMo Guardrails, Guardrails AI, Lakera Guard, and Azure Content Safety, with F1 and latency data.
- Defense
Secure RAG Architecture Best Practices for Production LLM Systems
A practitioner's guide to secure RAG architecture best practices: threat vectors, access control, retrieval isolation, and vector database hardening.
- Detection
Prompt Injection Detection Methods: A Practitioner's Guide
A comparative guide to prompt injection detection methods: classifier scanning, representation analysis, canary tokens, and output monitoring.
- Guardrails
How LLM Guardrails Work: Architecture, Detection, and Trade-offs
A technical breakdown of LLM guardrails: the six pipeline layers, classifier mechanics, latency costs, and the residual risks no single control covers.
- Defense
Choosing Runtime Guardrails for LLM Apps: A Decision Framework
There is no single best LLM guardrail. A framework for selecting runtime controls by threat, placement, and latency budget, with a worked example.
- Defense
Securing the ML Model Supply Chain: Signing and Verification
Model weights are unauthenticated binaries that execute code on load. A practical guide to model signing, provenance, and verification at load time.
- Monitoring
Monitoring LLM Outputs in Production: Anomalies and Drift
How to build production observability for LLM outputs, covering anomaly detection, latency alerting, output drift signals, and sane alert routing.
- Defense
Output Filtering Architecture for Production LLMs
How to architect a multi-layer output filtering pipeline for production LLMs: deterministic guards, classifiers, schema validation, and async sequencing.
- Defense
LLM Output Filter Latency: Budgeting Each Layer
What each output-filter layer costs in latency, from sub-millisecond regex checks to LLM-as-judge, and how to sequence them inside a real p95 budget.
- Defense
Prompt Injection Prevention: Defense in Depth
A systems-level guide to preventing prompt injection in production LLMs, covering layered controls, structural prompt design, and privilege separation.
- Defense
System Prompt Hardening Against Prompt Injection
How to harden an LLM system prompt against injection: explicit trust models, instruction hierarchy, and privilege separation between model roles.
- Defense
Implementing Rate Limiting and Abuse Detection for AI APIs
An engineering guide to rate limiting, quota enforcement, and abuse detection for AI APIs, covering token buckets and behavioral fingerprinting.
- Defense
Building an Internal Adversarial Testing Pipeline for LLMs
How to build an internal adversarial testing pipeline for LLM applications with garak, promptfoo, and custom probes, including a CI integration pattern.
- Defense
AI Defense Techniques for LLMs: A Practitioner's Guide
A technical breakdown of LLM defense techniques, from input guardrails and prompt hardening to dual-model architectures, mapped to OWASP and NIST.
- Defense
How to Implement LLM Guardrails: Input, Output, Tooling
Practical LLM guardrail patterns: input validation, output filtering, and monitoring, plus how NeMo Guardrails, Guardrails AI, and Llama Guard compare.