# Jailbreak Sandbox

> Test jailbreak techniques against progressively hardened defenses with simulated model responses and scoring.

- Source: https://stevenfoerster.com/lab/jailbreak-sandbox/

Lab

Test jailbreak techniques against progressively hardened defenses with simulated model responses and scoring.

Educational security demonstration

This tool simulates jailbreak outcomes without making real LLM API calls. All responses are pre-computed to demonstrate how different defense configurations affect attack success rates. No prompts are sent to any model.

What this is

An interactive sandbox for testing common LLM jailbreak techniques against layered defense configurations. See how each defense mechanism reduces attack effectiveness through pre-computed simulated outcomes.

What you'll learn

-   Common jailbreak technique categories
-   How defense layers interact and complement each other
-   Why defense-in-depth matters for LLM safety

## Technique Library

Select a jailbreak technique to test against the current defense configuration.

Persona Attack

Role-play framing to bypass restrictions

Encoding Bypass

Base64/ROT13/hex encoded instructions

Few-Shot Poisoning

Provide examples that establish harmful patterns

Multi-Turn Escalation

Gradually shift context across messages

Context Dilution

Overwhelm with benign tokens to bury instructions

Translation Chain

Use multiple languages to evade filters

## Defense Configuration

Enable defenses to see how they reduce jailbreak effectiveness.

All defenses off

Instruction Hierarchy

Prioritize system prompt over user input

System prompt priority

Effectiveness: High vs direct attacks

Input Sanitization

Detect and neutralize encoded payloads

Preprocessing filter

Effectiveness: High vs encoding

Output Filtering

Scan responses for policy violations

Post-generation check

Effectiveness: Broad but reactive

Constitutional AI

Self-critique and revision loop

RLHF + self-review

Effectiveness: Broad but imperfect

## Test Arena

Run the selected technique against the current defense configuration.

Run Test Reset

Select a technique above, then click **Run Test**.

Technique

\-

Defense Config

\-

Simulated Model Response

```
// Response will appear here
```

\-

Effectiveness Score

0

Explanation

\-

## Effectiveness Matrix

Overview of technique success rates across defense configurations. Scores represent jailbreak success likelihood (lower is safer).

Technique

## Understanding Jailbreak Techniques

### Persona Attacks

The attacker asks the model to role-play as an unrestricted character (e.g., "DAN" or a fictional villain). The persona framing shifts the model's context away from its safety training, making it more likely to comply with restricted requests.

### Encoding Bypasses

Harmful instructions are hidden in Base64, ROT13, hex, or other encodings. If the model decodes the payload internally, the safety filters on raw text may miss the intent. Input sanitization defenses target this by decoding before filtering.

### Multi-Turn Escalation

Rather than a single prompt, the attacker gradually shifts context across several messages, starting benign and slowly steering the conversation toward restricted territory. Each individual message looks innocuous, making detection harder.

### Effectiveness Scoring

The score (0–100) estimates how likely the jailbreak is to succeed against the current defense configuration. Each defense reduces the score by a technique-specific amount: encoding bypasses are heavily penalized by input sanitization, while persona attacks are more affected by instruction hierarchy.

Keyboard shortcuts

-   1-6 Select technique
-   Enter Run test
-   R Reset

Security model (30 seconds)

This tool runs entirely in your browser. No prompts are sent to any AI model - all responses are pre-computed and embedded in the page. No data is sent to any server. This is a pure simulation for educational purposes.

Further reading

-   [OWASP Top 10 for LLM Applications](https://owasp.org/www-project-top-10-for-large-language-model-applications/)
-   [Prompt Injection Visualizer (interactive injection simulation)](https://stevenfoerster.com/lab/prompt-injection/)