Security News > 2023 > November > Generative AI security: Preventing Microsoft Copilot data exposure
Copilot can access all the sensitive data that a user can access, which is often far too much.
In this post I'm going to focus specifically on data security and how your team can ensure a safe Copilot rollout.
The efficacy of label-based data protection will surely degrade when we have AI generating orders of magnitude more data requiring accurate and auto-updating labels.
We have already seen real-world scenarios in which Copilot drafts a proposal for a client and includes sensitive data belonging to a completely different client.
It's critical to have a sense of your data security posture before your Copilot rollout.
Varonis protects thousands of Microsoft 365 customers with our Data Security Platform, which provides a real-time view of risk and the ability to automatically enforce least privilege.
News URL
https://www.helpnetsecurity.com/2023/11/28/microsoft-copilot-data-exposure/
Related news
- Microsoft raises rewards for Copilot AI bug bounty program (source)
- Severe Security Flaws Patched in Microsoft Dynamics 365 and Power Apps Web API (source)
- Microsoft Sues Hacking Group Exploiting Azure AI for Harmful Content Creation (source)
- Microsoft Takes Legal Action Against AI “Hacking as a Service” Scheme (source)
- Microsoft sues 'foreign-based' cyber-crooks, seizes sites used to abuse AI (source)
- How AI and ML are transforming digital banking security (source)
- 3 Actively Exploited Zero-Day Flaws Patched in Microsoft's Latest Security Update (source)
- Microsoft eggheads say AI can never be made secure – after testing Redmond's own products (source)
- AI-driven insights transform security preparedness and recovery (source)
- Sage Copilot grounded briefly to fix AI misbehavior (source)