Copilot data, privacy and security
Microsoft's edit ·
Microsoft's commit message in MicrosoftDocs/microsoft-365-docs · commit d437717 · +1 −1 lines · also on GitHub
⋯ 191 unchanged lines
192192
193193
### Does Copilot block prompt injections (jailbreak attacks)?
194194
195
−Jailbreak attacks are prompts designed to bypass Copilot's safeguards or induce non-compliant behavior. Microsoft 365 Copilot helps mitigate these attacks by using proprietary jailbreak and cross-prompt injection attack (XPIA) classifiers. These classifiers analyze inputs to the Copilot service and help block high-risk prompts prior to model execution. These classifiers may not be available in all Microsoft 365 Copilot scenarios.
195
+Jailbreak attacks are prompts designed to bypass Copilot's safeguards or induce non-compliant behavior. Microsoft 365 Copilot helps mitigate these attacks by using proprietary techniques, such as jailbreak and cross-prompt injection attack (XPIA) classifiers. These classifiers analyze inputs to the Copilot service and help block high-risk prompts prior to model execution. These classifiers may not be available in all Microsoft 365 Copilot scenarios.
196196
197197
### What happens when foundation model changes occur?
198198
⋯ 15 unchanged lines
Microsoft's Markdown source from MicrosoftDocs/microsoft-365-docs, © Microsoft Corporation, under CC BY 4.0. Changed lines with up to 3 unchanged lines around each; ChangeIntel kept this copy 10 Oct 05:49 UTC. The commit date is when the source changed, which can be hours or days before Learn published it.