Grok exfiltrates user data when malicious instructions are encrypted
Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox. Now, a separate team has devised a similar attack against Grok. The new…
- 01.Earlier this week, researchers outlined an attack that used a secret input provided by Microsoft 365 Copilot for enterprise to cause the AI assistant to exfiltrate a password present in the user’s inbox
- 02.Now, a separate team has devised a similar attack against Grok
This material is provided as an extended analytical summary.
Read full article at sourceRelated Intelligence
All stories →OpenAI released GPT-6.1 Terra - AI that independently controls the computer
🤖 OpenAI has released GPT-6.1 Terra - an AI that independently controls a computer. The model can open applications, press buttons, fill out forms, write code and edit documents. In the demonstration, the neural network even created a 3D model of a tram in Blender from one photo.…
Frontier AI labs say their models refuted the Exponential Time Hypothesis. What does that mean?
TechCrunch spoke to the MIT computer scientist charged with explaining OpenAI's latest mind-bending discovery
Anthropic’s elaborate plan to keep Wall Street at bay
Anthropic cofounder and CEO Dario Amodei. | Bloomberg via Getty Images Anthropic wants to have it both ways. With its impending IPO, it wants to tap the vast riches of the public markets and insists it doesn't want to compromise its core mission of developing AI safely and for…