Jailbreaking
Crafting prompts that bypass a model's safety guardrails to elicit disallowed output.
Jailbreaking is the practice of crafting adversarial prompts that manipulate a foundation model into producing output it was trained or configured to refuse, such as harmful instructions or policy-violating text. Unlike prompt injection, which hijacks the application’s own system instructions, jailbreaking attacks the model’s underlying safety alignment directly, often through roleplay framing, hypothetical scenarios, or encoded language. Amazon Bedrock Guardrails, a feature of Amazon Bedrock, provides a dedicated defense layer that filters inputs and outputs, enforces denied topics, and applies content policies to resist these attempts rather than relying solely on the model’s built-in alignment.
PlayPrepHQ study notes are written and reviewed against primary exam sources. How we create & review content →