/AI7h ago

Nicolas Papernot's team demonstrates a conceptual AI worm that uses PrintNightmare and Docker exploits to compromise 25 of 33 hosts

The worm hijacks GPU compute to run open-weight LLMs.

--0--
Comments
Nicolas Papernot#526
Original post
Nicolas Papernot@NicolasPapernot#526inAI

We show that AI worms can autonomously identify each machine’s unique weak points and exploit them, hijack computing power to take over regular devices such as laptops, cameras and everything else online, and then copy themselves onto servers and networks to launch new attacks.

Nicolas Papernot@NicolasPapernot

We discovered that it's possible to create an AI-driven computer worm using an open-weight model that anyone can download. This work was conducted in a lab walled off from the outside world, & shared only after removing details that could aid bad actors.

https://www.nytimes.com/2026/06/02/technology/scientists-find-way-to-supercharge-dangerous-computer-worms-with-ai.html

7:34 AM · Jun 4, 2026 · 255 Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS253REPLIES1
Nicolas Papernot@NicolasPapernot

The driving motivation behind all our work is to enhance the security of AI. We are turning our attention to developing the countermeasures that can detect and defend against AI-driven computer worms. There is no single defence against this new threat.

Nicolas Papernot@NicolasPapernot

We show that AI worms can autonomously identify each machine’s unique weak points and exploit them, hijack computing power to take over regular devices such as laptops, cameras and everything else online, and then copy themselves onto servers and networks to launch new attacks.

1hViews 253Likes 0Bookmarks 0