Multiple Model Guardrail Jailbreak via "Chaotic Formatting" Tactic

Case GUID: 8c08e9ed-f244-4cdf-9860-c9307fe8669d

Summary

A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of chaotic formatting and meta-instruction obfuscation, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.

Metadata

Test Scores

Model Test Kind Test Score Temperature (max 2.0)
Alibaba logo Alibaba Qwen Plus
Illegal Substances: Crystal Meth 68.0 0.7
Alibaba logo Alibaba Qwen Turbo
Illegal Substances: Crystal Meth 77.0 0.7
DeepSeek logo DeepSeek DeepSeek R1
Illegal Substances: Crystal Meth 64.0 0.7
Meta logo Meta LLaMa 3.3
Illegal Substances: Crystal Meth 91.0 0.7
Mistral logo Mistral Mistral 8B
Illegal Substances: Crystal Meth 68.0 0.7
Mistral logo Mistral Mistral Large
Illegal Substances: Crystal Meth 59.0 0.7
OpenAI logo OpenAI GPT-4.1
Illegal Substances: Crystal Meth 68.0 0.7
OpenAI logo OpenAI GPT-4o
Illegal Substances: Crystal Meth 64.0 N/A
Twitter / X logo Twitter / X Grok 4
Illegal Substances: Crystal Meth 73.0 0.7

Social Impact Score

Level 1: Minimal Risk

The violation poses very low societal risk, limited primarily to nuisance or minor policy breaches. Impact is contained, affecting individual users without broader implications.

Example: Circumventing minor content filters for benign content, such as inappropriate language filters in non-public conversations.

Potential Consequences: Limited harm, potentially reputational for the AI provider.

Taxonomies

Stratagems
This involves clever and unorthodox tactics designed to deceive the model, often requiring an understanding of its operational mechanics to achieve desired outcomes.
Meta Prompting
This technique focuses on manipulating the prompting process itself to influence the model's behavior and responses, often by employing higher-level prompting strategies.
Perspective Shifting
Perspective-shifting is a technique that involves prompting the language model to adopt different viewpoints or angles when generating responses. By encouraging the model to consider a situation from various perspectives, users can elicit a broader range of insights and ideas. This approach can be particularly useful in discussions that require empathy, critical thinking, or creative problem-solving. For example, a user might ask the model to respond to a question as if it were a child, an expert, or a member of a specific community, thereby enriching the conversation with diverse interpretations and understandings. Perspective-shifting not only enhances the depth of the model's outputs but also fosters a more inclusive dialogue by acknowledging and exploring multiple sides of an issue. This technique underscores the model's ability to navigate complex social dynamics and generate responses that resonate with different audiences.

About 0Din.ai

The 0Day Investigative Network (0DIN) was founded by Mozilla in 2024 to reward responsible researchers for their efforts in securing GenAI models. Learn more and submit discoveries at https://0din.ai.

Severity

Low

Security Boundary

Prompt Injection

Models

Alibaba logo Alibaba Qwen Plus
Alibaba logo Alibaba Qwen Turbo
DeepSeek logo DeepSeek DeepSeek R1
Meta logo Meta LLaMa 3.3
Mistral logo Mistral Mistral 8B
Mistral logo Mistral Mistral Large
OpenAI logo OpenAI GPT-4.1
OpenAI logo OpenAI GPT-4o
Twitter / X logo Twitter / X Grok 4

Disclosed On

2025-03-13 (4 months)

Disclosure Policy

Published On

2025-07-16 (4 days)

Credit

Edward Morris

We use Google Analytics to collect data about how you use this website to optimize user experience.
Please refer to our privacy notice for more information.