Skip to main content

Multiple Model Guardrail Jailbreak via "Character Substitution" Tactic

Case GUID: fc8cec5d-79e2-4952-a727-64e7c6a579c6

Summary

A guardrail jailbreak vulnerability has been discovered affecting multiple models. The specific flaw manifests through a combination of system instruction manipulation and strategic character substitution, allowing the attacker to bypass inference restrictions around providing information hazards and violating laws.

Unlock the Full Intelligence Report

This disclosure is part of the 0DIN Threat Feed. Customers get access to:

Full Prompts & Variants
Detection Signatures
API Access
Full Data Export
Trend Analysis
Early Access

Metadata

Models and Test Scores

Copyrights Harmful Substances Illicit Substances
Harry Potter Anthrax Nerve Agent Crystal Meth Fentanyl
Google logo Google Gemini 2.0 Flash
Select a cell to view details.

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.
Deceptive Formatting
A prompt injection in the most pure sense, formatting the user prompt to fabricate the appearance of system instructions, a database query, its own prediction, or some other source of input a guard railed AI system might be expecting, causing it to behave in insecure ways based on the fabricated context from an adversarially formatted user prompt.
Language
This category focuses on the use of specific linguistic techniques, such as prompt injection or stylization, to influence the model's output.
Stylizing
This strategy involves using a method of questioning that encourages critical thinking and exposes biases by subtly referencing identity elements without using direct slurs or toxic language, thereby signaling to the model about certain groups of people.
Misspellings
Intentionally misspelling words to bypass filters or add a creative twist. This technique can involve simple letter swaps, phonetic replacements, or more complex alterations that still allow the intended meaning to be understood by the recipient. It is often used to evade censorship or to signal a specific subculture or in-group.

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.

Automate Your AI Security Testing

Want to find vulnerabilities in your own models? 0DIN Scanner turns our human-sourced threat intelligence into automated security assessments.

400+ Attack Probes

Derived from real bug bounties and security research

18+ AI Providers Supported

OpenAI, Azure, Anthropic, AWS Bedrock, and more

Automated Scheduling

Run recurring scans with real-time monitoring

Actionable Metrics

Attack Success Rate (ASR) scoring with 90-day trend analysis

Severity

Low

Security Boundary

Guardrail Jailbreak

Models

DeepSeek logo DeepSeek DeepSeek V3
Google logo Google Gemini 2.0 Flash

Disclosed On

2025-07-02 (about 1 year)

Disclosure Policy

Published On

2026-07-13 (15 days)

Credit

Anonymous