URL has been copied successfully!
Angreifer konnten verdeckte KI-Agenten in ChatGPT einschleusen
URL has been copied successfully!

Collecting Cyber-News from over 60 sources

Angreifer konnten verdeckte KI-Agenten in ChatGPT einschleusen


Tags: , , ,

Zenity Labs entdeckte die Schwachstelle AgentForger in ChatGPT Workspace Agents. OpenAI hat den Fehler kurz nach der Meldung behoben.

First seen on it-daily.net

Jump to article: www.it-daily.net/it-sicherheit/cybercrime/ki-agenten-in-chatgpt-einschleusen

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. Cybersecurity Snapshot: Top Advice for Detecting and Preventing AI Attacks, and for Securing AI Systems
  2. Researchers Find ChatGPT Vulnerabilities That Let Attackers Trick AI Into Leaking Data
  3. Schwachstelle im KI-Browser von OpenAI – Sicherheitslücke in ChatGPT Atlas erlaubt Übernahme von Nutzerkonten
  4. When AI safety constrains defenders more than attackers