Program Scope

0DIN's GenAI Bug Bounty targets security boundaries across models and apps. If you have questions, ask us.

STARTING

$500

MEDIUM

$2,500

HIGH

$5,000

SEVERE

$15,000

Model Security Boundaries

Vulnerabilities that target the model itself — its guardrails, extraction surface, code execution, content integrity, and weights.

Weights and Layers Disclosure

$15,000

Extracting or deducing a model's learned parameters and architectural details.

► REFERENCES

Content Manipulation

$5,000

Injecting harmful or misleading elements into data the model consumes or produces.

► REFERENCES

Interpreter Jailbreak

$2,500

Exploiting a model's ability to run code or invoke tools to escape its sandbox.

► REFERENCES

Guardrail Jailbreak

$500-$1,000

Bypassing a model's safety guardrails to produce restricted content.

► REFERENCES

Prompt Extraction

$100

Coercing a model into revealing its underlying system prompt.

► REFERENCES

In-Scope Models

Anthropic

1 model

Claude

Baidu

1 model

ERNIE

BigScience

1 model

BLOOM

Cohere

1 model

Command R

Google

2 models

Gemini

Gemini-Beta

Huawei

1 model

Pangu

IBM

1 model

Watson

Meta

1 model

LLaMa

Microsoft

1 model

CoPilot

NVIDIA

1 model

NeMo Megatron

OpenAI

1 model

GPT-4o

Salesforce

2 models

dsf

Einstein

SMASH Labs

1 model

PedModel 2030

Tencent

1 model

Hunyuan

Twitter / X

1 model

Grok

Prompt Extraction : test tooltip

Other

1 model

Other Models

Questions about scope? Reach out at 0din@mozilla.com