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
/ Saturday , September 14 2024
CISA issued 25 ICS advisories on September 12, 2024, detailing current security issues, vulnerabilities, and exploits in Industrial Control Systems....
Read More
By infosecbulletin
/ Friday , September 13 2024
Intel announced over 20 vulnerabilities in its processors and products in security advisories released on Tuesday. The chip giant has...
Read More
By infosecbulletin
/ Friday , September 13 2024
GitLab released security updates on Wednesday to fix 17 vulnerabilities, including a critical issue that lets attackers run pipeline jobs...
Read More
By infosecbulletin
/ Friday , September 13 2024
Fortinet confirmed a data breach after a threat actor claimed to have stolen 440GB of files from its Microsoft SharePoint...
Read More
By infosecbulletin
/ Thursday , September 12 2024
Indian Computer Emergency Response Team (CERT-In) issued a high-severity alert for android devices on September 11, 2024 highlighting the vulnerabilities...
Read More
By infosecbulletin
/ Thursday , September 12 2024
Because of disclosing incorrect and negative data, The Consumer Financial Protection Bureau (CFPB) on Wednesday fined TD Bank, one of...
Read More
By infosecbulletin
/ Thursday , September 12 2024
Bangladesh secure prestigious role-model position in the latest ITU cyber security index published by ITU. Bangladesh ranks among the top...
Read More
By infosecbulletin
/ Thursday , September 12 2024
Threatdown Managed Detection and Response (MDR) team has discovered the RansomHub ransomware gang using a new attack method wityh two...
Read More
By infosecbulletin
/ Wednesday , September 11 2024
India is to make 5,000 cyber commandos over the next five years to deal with cybercrimes in India, said Home...
Read More
By infosecbulletin
/ Wednesday , September 11 2024
In August, Cybersecurity researchers identified 21 new ransomware variants that threaten indivisual and business. Cybercriminals are improving their tactics, making...
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