A defensive course on Large Language Model (LLM) jailbreaking: what it actually means to persuade a model outside its trained safety behavior, how jailbreaking differs from prompt injection, jailbreak technique categories described conceptually without any working example or exploit-ready wording, why jailbreak resistance is trained and probabilistic rather than a patchable software defect, defense in depth through system prompt design, output-side filtering, and rate limiting with conversation-pattern monitoring, the elevated risk when a jailbroken model has agentic tool access, ongoing red teaming and incident response as standing practices, and an honest account of the current state of the field. This course teaches the concept, the risk pattern, and the defense only, and never provides a working jailbreak prompt or step-by-step bypass instruction.
Nothing. Every course, exam, and certificate on the catalog is free — including retakes. All you need is a free Safeguard account.
None. The flagship course, Safeguard Certified Practitioner, is a beginner-level course — basic familiarity with how software is built helps, but every exam question is answerable from the lessons themselves.
You can retake it after a 24-hour cooldown, as many times as you need. Retakes are free, and each attempt draws a fresh random set of questions.
The Safeguard Certified Practitioner credential is valid for 24 months from issue. The expiry date is printed on the certificate and shown live on its public verification page. Renewing means passing the current exam again.
