Last seen November 7, 2025

Microsoft Security Incident

The "Whisper Leak" is a novel side-channel attack that infers language model conversation topics by analyzing network packet sizes and timings, even when communications are protected by end-to-end TLS encryption. This allows attackers observing network traffic to deduce sensitive information about user prompts, posing significant privacy risks to users and enterprises.

Technical Severity
Low severity
Lifecycle Status

STABLE

What Happened

The "Whisper Leak" is a novel side-channel attack that infers language model conversation topics by analyzing network packet sizes and timings, even when communications are protected by end-to-end TLS encryption. This allows attackers observing network traffic to deduce sensitive information about user prompts, posing significant privacy risks to users and enterprises.

Why This Matters

Current evidence identifies a security issue involving Microsoft, but does not yet support a more specific impact claim.

Recommended Action

No confirmed vendor remediation is available in the current evidence. Confirm whether Microsoft is present in your environment and review the affected configuration.

Exposure

My AI Stack Exposure

Exposure unknown

Recommended Response
Last Seen

Nov 07, 2025 05:30

Exposure reason: This incident does not currently match a technology in My AI Stack.

Exploitation status: UNKNOWN

Primary entities:

MicrosoftWhisper Leak

Timeline

  • Incident first seen
    Nov 07, 2025 05:30

    BugSkan first recorded this incident.

  • ​​Whisper Leak: A novel side-channel attack on remote language models - Microsoft
    Nov 07, 2025 05:30

    microsoft.com · Research

Sources

​​Whisper Leak: A novel side-channel attack on remote language models - Microsoft

microsoft.com · Nov 07, 2025 05:30

The "Whisper Leak" is a novel side-channel attack that infers language model conversation topics by analyzing network packet sizes and timings, even when communications are protected by end-to-end TLS encryption. This allows attackers observing network traffic to deduce sensitive information about user prompts, posing significant privacy risks to users and enterprises.

Open publisher source

My AI Stack Match

Want personalized relevance?

Create an account to see which incidents overlap with your AI stack.

← Back to incident intelligence