Skip to content

For authorized AI red-teaming and defensive research only. Test systems you own or are permitted to test. Read the boundaries.

LLM Jailbreak Cheat Sheet

A quick-reference of common LLM jailbreak techniques with one-line how-it-works and one-line defense for each, for authorized red-team use.

Published on 4 min read

This is a fast lookup for the jailbreak families that AI red-teamers run against chat models. A jailbreak tries to make a model ignore its own safety policy through framing, role assignment, or output manipulation — distinct from prompt injection, which hijacks instructions through untrusted data. The two overlap and are often chained.

Important caveat: every technique below is model- and version-specific and decays. A payload that worked on one release is frequently patched in the next. Treat this table as a starting taxonomy for your own test harness, not a list of guaranteed bypasses. See OWASP LLM01: Prompt Injection (https://genai.owasp.org/llmrisk/llm01-prompt-injection/).

Authorized use only: run these against systems you own or are explicitly contracted to test.

Technique quick reference

TechniqueHow it works (one line)Defense (one line)
Persona / DAN ("Do Anything Now")Assign an alter-ego that "has no rules" so the model speaks as the unrestricted character.Anchor identity and policy in the system prompt; train the model to reject role reassignment that overrides safety.
AIM (Always Intelligent and Machiavellian)A fictional amoral advisor persona is asked to answer "without ethics or refusals."Same as persona defenses; classify requests for explicitly unethical/no-refusal personas and refuse them.
Developer / debug modeClaim a hidden maintenance mode exists that disables filters for "testing."Reject claims of privileged modes from user input; modes must come from authenticated, server-side configuration only.
Hypothetical / fiction framingWrap the disallowed request in a story, screenplay, or "purely hypothetical" scenario.Apply policy to the content of the output, not the wrapper; classify on intent, not the fictional frame.
Grandma exploitEmotional roleplay ("my late grandma used to read me...") to coax restricted content as comfort.Detect emotionally framed pretexts; evaluate the requested payload independently of the sympathetic story.
Prefix injectionForce the reply to begin with a compliant opener ("Sure, here is...") so it continues down that path.Output-side classification on full responses; do not let a forced prefix short-circuit refusal logic.
Refusal suppressionInstruct the model to never apologize, never say "I can't," and avoid refusal vocabulary.Make refusal a hard policy outcome, not a stylistic choice the prompt can disable.
Many-shot jailbreakingStuff the context with dozens/hundreds of fake Q&A pairs where the assistant always complies, then ask the real question.Limit/scan long in-context example blocks; safety tuning robust to many-shot; monitor context for compliance-priming patterns.
CrescendoStart benign and escalate over several turns, each step a small increment toward the disallowed goal.Evaluate conversation-level trajectory, not just the latest turn; reset risk scoring across the dialogue.
Payload splittingBreak the disallowed instruction across variables/turns and have the model concatenate and execute it.Reassemble and re-evaluate combined content before acting; classify the assembled result, not the fragments.

Why these keep working (briefly)

Most jailbreaks exploit the same root cause: the model treats the entire prompt as a single instruction space, with no hard boundary between "policy" and "user-supplied roleplay." Persona, fiction, and mode-claim attacks all try to relocate the request into a context where the model believes the rules do not apply. Prefix and refusal-suppression attacks instead attack the output shape, betting that once the model starts complying it will continue. Many-shot and crescendo are statistical: they bias the model with overwhelming in-context precedent or gradual normalization.

Defenses (layered)

No single control stops jailbreaks. Combine:

  • System-prompt hardening — state non-negotiable policy, refuse role/mode reassignment, and place safety instructions where user text cannot overwrite them.
  • Input and output classification — screen prompts and full responses with a separate safety model; classify on intent and content, ignoring fictional or emotional wrappers.
  • Conversation-level monitoring — score the whole dialogue to catch crescendo and multi-turn payload assembly, not just the current message.
  • Context hygiene — cap and inspect long example blocks to blunt many-shot priming.
  • Continuous red-teaming — because techniques decay and mutate, re-run an automated suite against every model/prompt change and track regression.

How to test it safely

Keep a versioned harness of these payloads mapped to expected-refusal cases. Run it on each model upgrade or system-prompt change, record pass/fail per technique, and treat any new pass as a regression to fix. Only test systems you are authorized to assess, and avoid generating genuinely harmful artifacts — use canary/benign proxies where possible to confirm a bypass without producing real harm.

Related articles

Quick reference for encoding and obfuscation bypasses used in prompt injection, with tiny examples and defenses like normalization and Unicode filtering.
What authorized testing means for LLM apps: written scope, why prompt-injection research is legitimate for defenders, responsible disclosure, and what never to do.
The classic markdown-image beacon: how indirect prompt injection turns an auto-loaded image into a data-leak channel, and how to shut it down.