Microsoft Offers Up to $30,000 for Critical AI Flaws in Dynamics 365 and Power Platform
Microsoft expands AI bug bounty to Dynamics 365 and Power Platform, paying up to $30,000 for critical inference manipulation flaws.
Microsoft's bug bounty program offers up to $30,000 for critical 'Inference Manipulation' or 'Inferential Information Disclosure' bugs in Dynamics 365 and Power Platform, including Copilot Studio, AI Builder, Power Apps, Power Automate, and Dataverse. Payouts scale by report quality ($30,000/$20,000/$12,000 for critical) with important-severity AI flaws earning $6,000-$20,000, plus 20% multipliers for Dataverse privilege escalation and Plugin Sandbox escapes. Prompt injection affecting only the attacker, hallucinated execution, and system-prompt disclosure are excluded from scope.
- Maximum $30,000 for critical inference manipulation or information disclosure flaws
- Scope covers Dynamics 365, Power Apps, Power Automate, Copilot Studio, AI Builder, Dataverse
- 20% multiplier for Dataverse privilege escalation and Plugin Sandbox escapes
- Self-affecting prompt injection and content-safety issues excluded
From the original article
3 min read at cybersecuritynews.com
Microsoft is offering security researchers up to $30,000 for finding critical AI vulnerabilities in Dynamics 365 and Power Platform, sharpening its focus on flaws that could manipulate AI inference or expose information through model behavior. The program covers qualifying bugs in Microsoft-hosted services and third-party or open-source components embedded in them, provided researchers demonstrate a […]
By Guru Baran · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.