arXiv AI By Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud, Christopher Amato, Alina Oprea, Eugene Bagdasarian

Targeting World Models to Compromise Robot Learning Pipelines

Read the original on arXiv AI →

arXiv:2606. 09499v1 Announce Type: cross Abstract: World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world environments, with many works proposing their integration into the robot learning pipeline.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Aug 5

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain

arXiv:2510. 05159v5 Announce Type: replace-cross Abstract: While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain.

By L\'eo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru, Nazanin Sepahvand, Nicolas Chapados, Quentin Cappart, Jason Stanley, Alexandre Lacoste, Krishnamurthy Dj Dvijotham, Alexandre Drouin
arXiv AI
Jun 3

Phantom Transfer: Data Poisoning can Survive Data-Level Defences

arXiv:2602. 04899v2 Announce Type: replace-cross Abstract: We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out.

By Andrew Draganov, Tolga H. Dur, Anandmayi Bhongade, Mary Phuong