URL has been copied successfully!
MINJA sneak attack poisons AI models for other chatbot users
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

MINJA sneak attack poisons AI models for other chatbot users


Tags: , , ,

Nothing like an OpenAI-powered agent leaking data or getting confused over what someone else whispered to it

First seen on theregister.com

Jump to article: www.theregister.com/2025/03/11/minja_attack_poisons_ai_model_memory/

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. Gen AI is transforming the cyber threat landscape by democratizing vulnerability hunting
  2. Cross-post: Office of the CISO 2024 Year in Review: AI Trust and Security
  3. ChatGPT Operator Prompt Injection Exploit Leaks Private Data
  4. Securing the backbone of enterprise generative AI