WorksComputer Science

Can Open Be Too Open? On the Security and Trustworthiness of Fully Transparent LLMs

Sheila Zingg, Florian Tramèr, Martin Vechev, Srdjan Čapkun

Published Oct 26, 2026Fresh — added to the Hub within the last 30 daysv1

Versions

PDFs, citations, reviews, and endorsements stay with each version.

1 versionNewest first

v1
LatestRead version
Oct 30, 2026Viewing

Beginning of version history