Checked fact 132713 Oct 2026Research

The abstract says that, using digital lockers, "these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights".

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights

What the source said when we opened it, on 13 Oct 2026.

The source

AI Models Can Provably Hide Arbitrary Capabilities
arXiv · 2026-10-09

Open the source archived copy

Checked

Checked by the notis newsroom on 13 Oct 2026, against the source above.

In the story

Authors say backdoored models can hide encrypted capabilities provably hard to elicit 13 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The abstract says that, using digital lockers, "these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights".” ai notis, checked 13 Oct 2026. Source: AI Models Can Provably Hide Arbitrary Capabilities (arXiv). https://ainotis.com/c/1327

As a reference (APA style)

ai notis. (2026, October 13). The abstract says that, using digital lockers, "these hidden circuits remain provably hard to elicit and interpret under cryptographic assumptions, even given full access to model weights" [Checked claim 1327]. ai notis. https://ainotis.com/c/1327

Anyone may quote this address. It does not change; if we correct the story, this page says so.