Weekly digest
Obfuscated Weekly
AI security research, red teaming findings, and compliance updates — written for practitioners, delivered every week.
Subscribe
What's inside
- Attack techniques Prompt injection, jailbreaks, agent hijacking, model extraction — how they work and how they're evolving.
- Defensive architecture Patterns for building AI systems that are harder to compromise and easier to audit.
- Compliance & regulation EU AI Act, NIST AI RMF, ISO 42001 — what changed, what it means, what you actually need to do.
- Tool reviews Hands-on with Promptfoo, Garak, PyRIT, and whatever else is worth your time.
- Original research Experiments, findings, and analysis you won't find in a vendor whitepaper.