URL has been copied successfully!
Researchers Hacked AI Assistants Using ASCII Art
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

Researchers Hacked AI Assistants Using ASCII Art

by

Andy Stern
in

Tags: , ,

Large language models (LLMs) are vulnerable to attacks, leveraging their inability to recognize prompts conveyed through ASCII art.  ASCII art is a fo…

First seen on gbhackers.com

Jump to article: gbhackers.com/ascii-art-ai-assistant-hack/

Loading

Share via Email
Share on Facebook
Tweet on X (Twitter)
Share on Whatsapp
Share on LinkedIn
Share on Xing
Copy link

also interesting:

  1. New Hugging Face Vulnerability Exposes AI Models to Supply Chain Attacks
  2. AI-As-A-Service Providers Vulnerability Let Attackers Perform Cross-Tenant Attacks
  3. Vulnerabilities Exposed Hugging Face to AI Supply Chain Attacks
  4. Nvidia Patches High-Severity Flaws in GPU Drivers