Microsoft has launched a new AI bounty program. This program is the result of investments and learnings from recent months, including an AI security research challenge and an update to Microsoft’s vulnerability severity classification for AI systems. Lynn Miyashita, a technical program manager with the Microsoft Security Response Center, shared this information.
The Microsoft AI bug bounty program
Microsoft wants bug hunters to test AI-powered Bing features on bing.com using a browser. They also want them to test Bing integration on Microsoft Edge, including Bing Chat for Enterprise. Additionally, they want testers to check the Bing integration in the iOS and Android versions of Microsoft Start and Skype mobile apps.
They should report vulnerabilities that could be exploited to:
* Manipulate the model’s response to individual inference requests, but do not modify the model itself (“inference manipulation”)
* Manipulate a model during the training phase (“model manipulation”)
* Infer information about the model’s training data, architecture and weights, or inference-time input data (“inferential information disclosure”)
* Influence/change Bing’s chat behavior in a way that impacts all other users
* Modify Bing’s chat behavior by adjusting client and/or server visible configuration
* Break Bing’s cross-conversation memory protections and history deletion
* Reveal Bing’s internal workings and prompts, decision making processes and confidential information
* Bypass Bing’s chat mode session limits and/or restrictions/rules
Click here to read more