URL has been copied successfully!
It Takes Only 250 Documents to Poison Any AI Model
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

It Takes Only 250 Documents to Poison Any AI Model


Tags:

Researchers find it takes far less to manipulate a large language model’s (LLM) behavior than anyone previously assumed.

First seen on darkreading.com

Jump to article: www.darkreading.com/application-security/only-250-documents-poison-any-ai-model

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. PyRIT: Open-source framework to find risks in generative AI systems
  2. Hugging Face Vulnerabilities Highlight AI-as-a-Service Risks
  3. Verteidigung gegen Deepfake-Attacken
  4. GitHub Copilot ‘CamoLeak’ AI Attack Exfiltrates Data