Skip to content
Whisper Leak: Side-Channel Attack on LLMs Exposed

Whisper Leak: Side-Channel Attack on LLMs Exposed

First seen 2 Dec 2025, 18:33 UTC • •

Article Content

Browse articles
ThreatCluster AI
ThreatCluster •March 12, 2026 at 13:27 UTC

Microsoft has identified a side-channel attack, termed 'Whisper Leak', that enables attackers to deduce the conversation topics of language models, even when communications are encrypted. This vulnerability affects users relying on end-to-end encryption for secure interactions with chatbots.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Updated 213d ago How this analysis works

More articles in this cluster (2)