By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Model level hardening

Model providers train models to rank system and developer instructions above text found in tool results. Knowing how instruction hierarchy, structured queries and preference tuning work helps you judge vendor claims and pick models for high-risk agents.

Read in this order

  1. PaperThe Instruction Hierarchy: Training LLMs to Prioritize Privileged InstructionsStart here: the instruction hierarchy idea and how it is trained.
  2. PaperLessons from Defending Gemini Against Indirect Prompt InjectionsLessons from a vendor defending a production model, including what failed.
  3. PaperSecAlign: Defending Against Prompt Injection with Preference OptimizationPreference tuning against injection, with measured attack success rates.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.