Are conversations with AI chatbots safe? Microsoft uncovers a serious flaw that could expose your personal chats

12 Nov 2025 | Category: Technology

A new vulnerability, ‘Whisper Leak’, could allow attackers to infer topics discussed with AI chatbots by analysing network traffic patterns, Microsoft has warned. The company also highlighted the risks of surveillance by oppressive governments targeting sensitive discussions.

Microsoft has warned about a new kind of side-channel attack that can reveal to an attacker what a user is talking about with an AI chatbot like ChatGPT or Gemini. The vulnerability, called “Whisper Leak”, would not give attackers the chance to read ...

🔗 Read More at Original Source