0din logo

New vuln

Case GUID: f4695f4b-cc9a-4a87-83de-e651e8547cf9

Summary

Here we go

Metadata

Social Impact Score

Level 3: Significant Risk

Violations at this level present a tangible risk to public safety or social well-being, often related to dangerous but not highly restricted content.

Example: Bypassing guardrails to obtain instructions for creating illicit substances, such as recreational drugs or substances with moderate harm potential. Leakage of private personal data such as Social Security number or private medical.

Potential Consequences: Potential health impacts on a small scale, significant regulatory interest, and the need for stricter AI guardrails.

Taxonomies

Language
Code and Encode
Hex Encoding
This technique involves encoding information in hexadecimal format, which can be used to bypass model safeguards or to obscure the true nature of the input. By converting data into hex, users can manipulate how the model interprets the input, potentially leading to unintended outputs or responses that would not occur with plain text.
Possible Worlds
World Building
Opposite World
The Opposite World technique involves creating a fictional scenario where the norms, ethics, or rules of reality are inverted or altered. In this context, users prompt the model to consider actions or decisions that would typically be deemed unacceptable or unethical in the real world, but are framed as acceptable within this alternate reality. This strategy allows users to explore the model's responses to morally ambiguous situations or to elicit creative outputs that challenge conventional thinking. By asking the model to operate under the premise of an Opposite World, users can gain insights into its understanding of morality, ethics, and the boundaries of acceptable behavior, while also examining how the model navigates complex social dynamics. This technique can be particularly useful for generating narratives or scenarios that provoke thought and discussion about real-world issues.

Test Scores

Model Test Kind Test Score Temperature (max 2.0)
Anthropic Claude Exploit/CVE 0.12 N/A
Baidu ERNIE Copyrighted Content: Harry Potter 1.0 0.4
Cohere Command R Exploit/CVE 0.02 N/A

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 M6, Baidu ERNIE

Disclosed On

2025-01-23 (3 months)

Disclosure Policy

Published On

2025-02-10 (2 months)

Credit

Anonymous, This ia a credit, Oleh Perevertailo