Topics
Browse posts by category and tag — every topic we cover, with the latest pieces under each.
Tags
- #open-source 7
- #llm-security 5
- #red-team 5
- #ai-security 3
- #garak 3
- #llm-scanner 3
- #product-review 3
- #prompt-injection 3
- #ci-cd 2
- #enterprise 2
- #hallucination-detection 2
- #microsoft 2
- #owasp-llm 2
- #pyrit 2
- #vulnerability-scanning 2
- #ai-firewall 1
- #ai-guardrails 1
- #ai-red-teaming 1
- #algorithmic-red-teaming 1
- #arize-phoenix 1
- #cisco-ai-defense 1
- #framework 1
- #giskard 1
- #guardrails 1
- #guardrails-ai 1
- #lakera 1
- #llm-evaluation 1
- #llm-mitigation 1
- #llm-monitoring 1
- #llm-safety 1
- #llm-testing 1
- #ml-supply-chain 1
- #ml-testing 1
- #model-security 1
- #modelscan 1
- #nbdefense 1
- #nvidia 1
- #observability 1
- #output-validation 1
- #patronus-ai 1
- #procurement 1
- #production 1
- #protect-ai 1
- #rag 1
- #rag-evaluation 1
- #raget 1
- #rebuff 1
- #red-teaming 1
- #robust-intelligence 1
- #self-hosted 1
- #structured-output 1
- #supply-chain 1
- #tool-evaluation 1
- #validators 1
- #vendor-evaluation 1
- #vulnerability-testing 1
Categories
reviews 12 posts
- Patronus AI Review: Automated LLM Evaluation and GuardrailsA review of Patronus AI's evaluation platform — the Lynx hallucination model, the Glider custom evaluator, the built-in judge and safety evaluators, and
- Protect AI's ModelScan and NB Defense: Open-Source AI Supply-Chain ScanningA hands-on review of Protect AI's two best-known open-source tools — ModelScan for model serialization attacks and NB Defense for Jupyter notebooks.
- Robust Intelligence (Now Cisco AI Defense): What the Platform Actually CoversA conservative review of Robust Intelligence — the AI security pioneer now part of Cisco AI Defense. Algorithmic red teaming, AI Validation, model file
- Giskard Review: Open-Source Testing and Evaluation for LLM and RAG AppsA long-form review of Giskard, the open-source Python library for testing AI systems. Its automated Scan for LLM vulnerabilities, the RAGET RAG-evaluation
- Garak Deep Dive: Architecture, Probes, and Operating the NVIDIA LLM ScannerA hands-on, long-form review of garak — NVIDIA's open-source LLM vulnerability scanner. How its probe/detector/generator/buff architecture actually works
- PyRIT Deep Dive: Microsoft's AI Red Teaming Framework in PracticeA long-form review of PyRIT, Microsoft's open-source AI red teaming framework. Its orchestrator/target/converter/scorer/memory architecture, multi-turn