Skip to main content

0DIN bug bounty program

Last Updated: 2026-10-02

Introduction

Mozilla's 0Day Investigative Network (“0DIN”) is a GenAI bug bounty program that incentivizes the third party (“Researcher(s)”) discovery and reporting of security vulnerabilities in large language models, attention-based systems and other generative models to enhance Internet and personal safety (“Program”). These 0DIN Bug Bounty Program Terms and Conditions (“Terms”) govern your use and participation of the Program.

Vulnerability Bounty

  • Rewards range from $500 to $15,000 based on impact, report quality, and timing of submission as set forth in the "Duplicate Discoveries" section below.
  • Bounties are discretionary and are evaluated by the 0DIN team.
  • As a generality: Low severity up to $500, Medium up to $2,500, High up to $5,000, and Severe up to $15,000.
  • Researchers will be credited in the final advisory and may remain anonymous if they choose. However, Researchers have the option to make their profile information and submission statistics publicly available in our leaderboard.
  • Eligible bugs must be original, unreported / non-public, affect the latest available model generation.
  • Duplicate submissions will share the bounty as set forth in the "Duplicate Discoveries" section below.
  • Researchers are encouraged to use test accounts and avoid harming service availability or stability.
  • Submission details must be kept confidential during the validation period (two weeks). If contracted, then the confidentiality period extends through the coordinated public disclosure date as per our disclosure policy below.
  • Bounties can be donated to any of the following charities: AccessNow, Asociación por los Derechos Civiles, Association for Progressive Communications (APC), Center for Democracy & Technology, Center for Internet and Society Bangalore, Derechos Digitales, Electronic Frontier Foundation (EFF), EngageMedia, European Digital Rights (EDRi), Internet Archive, ITS-Rio, Kenya ICT Action Network (KICTANet), OpenNet Korea, Privacy International, R3D, SimplySecure, SMEX, Tactical Tech, The Guardian Project, Tor Project, Wikimedia Foundation.
  • This is a rapidly evolving space and these terms and conditions are subject to change. Researchers who we have engaged with will receive notification of such changes.

Account Creation

You will need to create an account via the 0din.ai portal to submit your discovery. During account registration, you will need to provide a valid email address, password, country code, first name, and last name.

Privacy

We use the information we receive through the 0DIN portal as described in our Privacy Notice.

Vulnerability Scope

  • Commonly adopted GenAI models and applications including but not limited to those from OpenAI, Meta, Google, Anthropic, SalesForce, etc.
    • Affected models can be commercial and/or open source.
    • Affected models should be commonly used.
  • Eligible model bugs must exist within the models themselves, as opposed to the software ecosystem around the model. Examples along with their starting severities include but are not limited to:
    • Prompt Extraction, LOW
      • Unauthorized extraction of original inputs or queries that were provided to the model.

    • Guardrail Jailbreak, LOW to HIGH
      • Insertion of malicious or altered prompts into the model to manipulate outputs or jailbreak guardrails.

    • Interpreter Jailbreak, MEDIUM
      • Bypassing the execution environment restrictions of an LLMs interpreter to execute arbitrary code.

    • Content Manipulation, HIGH
      • Predictably injecting harmful or misleading data into that the model consumes or produces.

    • Weights and Layers Disclosure, SEVERE
      • Extracting the intellectual property of a closed model such that it can be replicated.

    • For more up to date information, please see “Scope” under our website 0din.ai.

  • Eligible application bugs start with a prompt injection and must result in unauthorized actions, for example:
    • Read Violation, LOW to MEDIUM
      • Unauthorized data exfiltration through the app.

    • Write Violation, MEDIUM to HIGH
      • Unauthorized data modification through the app.

    • Execute Violation, HIGH to SEVERE
      • Unauthorized command or code execution through the app.

  • When in doubt, contact us with the model name and high-level boundary violation for review (see Abstract Sign-off below).

Eligible Participants

  • You must not exploit the security vulnerability for your own gain.
  • You must not be an employee, contractor, or otherwise have a business relationship with the Mozilla Corporation or any of its affiliates.
  • You must not be an employee, contractor, or otherwise have a business relationship with the company that makes the software or service for which you are reporting a vulnerability.
  • You must not have contributed to or be responsible for the vulnerability.
  • All submissions will be covered under Mozilla's Website & Communications Terms of Use, granting us permission to make use of all submissions. To the extent that there are conflicting terms between the Mozilla Website & Communications Terms of Use and these Terms, these Terms will apply only to the extent of the conflict.
  • You must be the age of majority to be eligible to participate in and receive payment from this Program in your jurisdiction, or otherwise qualify to receive payment, whether through consent from your parent or guardian or some other way.
  • You must not be on a US sanctions list or in a country (e.g. Cuba, Iran, North Korea, Crimea region of Ukraine, Sudan, and Syria) on the US sanctions list.
  • All questions regarding the status of 0din bounties should be directed to 0din@mozilla.com and not other Mozilla bug bounty programs.

Vulnerability Processing and Disclosure Policy

Abstract Sign-off and Bounty Range

This is a novel space, to ensure we’re on the same page we recommend that Researchers initially submit a high-level abstract of their findings and list the affected model(s). Within 3 business days we will respond with a decision on whether or not the flaw is within scope and what the likely range of bounty will be. The Researcher can then decide to progress by submitting full details of the discovery.

Validate Submitted Information

We attempt to validate the information submitted by Researchers within 2 weeks. During this period, our team will thoroughly assess the vulnerability to confirm its validity and impact. If the complexity of the submission requires further time for validation, we’ll let the Researcher know early in this process.

In the event that our team is experiencing a heavy load, researchers will be informed of load status via the 0DIN portal. This transparency helps set expectations regarding the timeline for validation and further communication.

Duplicate Discoveries

The security bug must be original and previously unreported. Duplicate submissions of Medium or higher severity received within 7 days from the date and time of first submission will split the bounty between the Researchers. If duplicate submissions are of unequal quality, the split will be at the level of the lesser report, and the greater report will receive a prorated additional bounty on top of the split. 0DIN will determine the eligibility of the submissions using its internal database clock.

For submissions of Low severity, the first submission receives 100% of the bounty, the second submission receives 50% bounty, the third submission 20% bounty, and the remainder simply share credit, provided that the security vulnerability has not been already disclosed to the vendor or publicly disclosed through any channels prior to submission.

Please see our Program Scope for more information about the bounty scopes.

Additional Features and Bug Bounty Opportunities

Researchers with a proven track record of submitting quality vulnerabilities may be provided access to additional features and opportunities at 0DIN’s discretion. Access to these tools and opportunities may be subject to additional terms and requirements which will be provided to Researchers prior to accessing such feature or opportunity.

Researcher Payment

We commit to submitting payment to Researchers within 30 days of reaching a contractual agreement. This ensures that Researchers are compensated promptly for their contributions. Bounties can be donated to certain charities (see above), and should be indicated by the Researcher during the submission process.

As a matter of both policy and law, we must know who we are paying. Researchers must submit a valid government issued photo identification (ex: passport, drivers license) to be eligible for payment. Researchers are responsible for their own tax obligations in light of the reward. US based Researchers must provide a completed IRS W-9 form. Non-US based Researchers must provide a completed IRS W-8 form.

Vendor Notification

We will attempt to contact the affected vendor via publicly listed contact information after reaching a contractual agreement with the Researcher to provide an overview of the vulnerability. We will check the vendor’s website for registered contacts via “.well-known/security.txt” (RFC 9116). If a formal security contact is unavailable, we will attempt to reach the vendor using the following email addresses: psirt@, security@, secure@, support@, and info@. If we successfully connect with the vendor, the vendor may opt-in to receive the full vulnerability report details for the applicable vulnerability disclosed in our vendor notification.

Public Disclosure Timeline

For model vulnerabilities, we will publish details of the vulnerability once we determine, in our sole discretion, that the vulnerability has been mitigated so that it no longer materially impacts mainstream models.

For application vulnerabilities, if we are unable to connect with the vendor after three attempts over a two-week period, we will proceed with public disclosure of the vulnerability within 30 days. This ensures that the information is made available to the public in a timely manner to mitigate potential risks. If we successfully connect with the vendor, we will provide them with up to 4 months (120 days) to address the issue before public disclosure. This time frame allows the vendor sufficient time to develop and deploy a fix while ensuring that the vulnerability is eventually disclosed.

Public Disclosure

Once the public disclosure requirements have been met, we will post and advertise the vulnerability publicly. The 0DIN team will handle this process, and we will provide (optional) credit to the discovering Researcher, acknowledging their contribution to improving security.

By adhering to this policy, we aim to balance the need for public awareness of vulnerabilities with the necessity of giving vendors adequate time to address security issues. Our goal is to foster a collaborative environment that enhances overall cybersecurity.

Questions

If you have any questions, comments or concerns do not hesitate to reach out to us at 0din@mozilla.com.