Topics
Browse posts by category and tag — every topic we cover, with the latest pieces under each.
Tags
- #guardrails 6
- #red-teaming 4
- #llm-security 3
- #open-source 3
- #ai-safety 2
- #content-moderation 2
- #garak 2
- #llama-guard 2
- #llm-guard 2
- #nemo-guardrails 2
- #pyrit 2
- #vulnerability-scanning 2
- #ci-cd 1
- #classifier-on-output 1
- #detection 1
- #evaluation 1
- #false-positives 1
- #guardrails-ai 1
- #input-scanning 1
- #meta 1
- #microsoft 1
- #openai-moderation 1
- #output-scanning 1
- #post-generation 1
- #prompt-injection 1
- #promptfoo 1
- #protect-ai 1
- #rebuff 1
- #refusal-tuning 1
- #safety-utility-tradeoff 1
- #vigil 1
Categories
tools 5 posts
- Automated LLM Red-Teaming in CI: garak vs PyRIT vs PromptfooThree open-source tools can gate your pipeline on LLM security findings — garak, PyRIT, and Promptfoo. A practitioner comparison of how each fits CI/CD, what it scans, and which to run where.
- Prompt-Injection Detectors Compared: Rebuff, Vigil, and LLM GuardA practitioner comparison of open-source prompt-injection detectors — Rebuff, Vigil, and LLM Guard's PromptInjection scanner — including detection architecture, maintenance status, and which to actually deploy in 2026.
- PyRIT: Microsoft's AI Red-Teaming Framework, ExplainedA technical breakdown of PyRIT, Microsoft's Python Risk Identification Tool for generative AI — its target/dataset/orchestrator/converter/scorer architecture, multi-turn attack strategies, and where it fits next to garak.
- Best LLM Security Scanners: Open-Source and Enterprise ComparedA practitioner's comparison of the best LLM security scanners — Garak, PyRIT, LLM Guard, Promptfoo, Vigil, and enterprise options. Coverage, CI/CD fit, and runtime use cases.
- Garak LLM Vulnerability Scanner: How It Works and When to Use ItA technical breakdown of the garak LLM vulnerability scanner — its probe architecture, supported attack categories, CLI workflow, and how it fits into a real AI red-teaming pipeline.
guardrails 4 posts
- Choosing an LLM Guardrail: Llama Guard, NeMo Guardrails, Guardrails AIA decision guide for picking an LLM guardrail in 2026 — Meta's Llama Guard 4, NVIDIA's NeMo Guardrails, and Guardrails AI. What each one actually is, and which shape fits your problem.
- LLM Guard: Input and Output Scanning for Production LLM AppsA practical breakdown of LLM Guard by Protect AI — its input and output scanners, how the sanitize/scan pipeline works, where it fits as a runtime guardrail, and its real limits.
- Classifier-on-Output: Catching Misbehavior Post-GenerationHow production teams use post-generation classifiers to catch what input filters and refusal training miss — architectures, tradeoffs, and where output classifiers earn their latency budget.
- Llama Guard vs NeMo vs OpenAI Moderation: Production TradeoffsA practitioner comparison of Llama Guard, NeMo Guardrails, and the OpenAI Moderation API — coverage, latency, customization, and where each one breaks in production.