Security researchers created an algorithm that turns a malicious prompt into a set of hidden instructions that could send a user’s personal information to an attacker.
Source: Wired – Threat Level
This Prompt Can Make an AI Chatbot Identify and Extract Personal Details From Your Chats
- How Ransomware Jeopardizes Healthcare Organizations
- Are Identity Theft Protection Services Worth the Money? It’s Complicated
- Week in review: Microsoft patches actively exploited 0-days, Amazon and HSBC employee data leaked
- Google’s Gemini AI Chatbot Keeps Telling Users to Die
- Cybersecurity Flaws in US Drinking Water Systems Put 26 Million at Risk