Morris II: The First Self-Propagating Worm for Generative AIs
Faits validés
Researchers from Cornell Tech and Technion (Cohen et al., 2024, ComPromptMized). Demonstrates creating an autonomous worm that breaks GenAI email-assistant safety barriers, steals data, and forwards itself to new recipients.
En termes simples
A chain letter that rewrites itself: The AI opens an email, gets infected, steals your address book, and sends the infection on to all your contacts.
Pertinence sécurité & conseil pratique
Illustrates why fully automated AI workflows without human checkpoints are dangerous.