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
By infosecbulletin
/ Wednesday , January 22 2025
Fortinet customers must apply the latest updates, as almost 50,000 management interfaces remain vulnerable to the latest zero-day exploit. The...
Read More
By infosecbulletin
/ Tuesday , January 21 2025
Every day a lot of cyberattack happen around the world including ransomware, Malware attack, data breaches, website defacement and so...
Read More
By infosecbulletin
/ Tuesday , January 21 2025
Ubuntu 22.04 LTS users are advised to update their systems right away due to a crucial security patch from Canonical...
Read More
By infosecbulletin
/ Tuesday , January 21 2025
Attackers are pretending to be Ukraine's Computer Emergency Response Team (CERT-UA) using AnyDesk to access target computers. “Unidentified individuals are...
Read More
By infosecbulletin
/ Tuesday , January 21 2025
Oracle Critical Patch Update Pre-Release Announcement shares details about the upcoming update scheduled for January 21, 2025. Note that this...
Read More
By infosecbulletin
/ Tuesday , January 21 2025
OWASP has released its updated list of the top 10 vulnerabilities in smart contracts for 2025. This guide highlights the...
Read More
By infosecbulletin
/ Monday , January 20 2025
Security researchers have found several vulnerabilities in Azure DevOps that could enable attackers to inject CRLF queries and carry out...
Read More
By infosecbulletin
/ Monday , January 20 2025
Intel Corporation is a leading semiconductor chip manufacturer, employing at least 22 graduates from the Department of Applied Chemistry and...
Read More
By infosecbulletin
/ Sunday , January 19 2025
vpnMentor’s Research Team is monitoring the potential TikTok ban in the U.S., driven by national security and data privacy issues....
Read More
By infosecbulletin
/ Saturday , January 18 2025
MITRE launched D3FENDTM 1.0, a cybersecurity framework that provides a vocabulary and understanding of the cyber domain. D3FEND 1.0, funded...
Read More
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