0

A Backdoor Trigger Is Legible in Fine-Tune Weights

A backdoored language model behaves normally until a trigger phrase appears in its input. Every published method for recovering such a trigger runs the model. We show the trigger is legible in the weights alone: a static statistic reads a fine-tuned checkpoint with no forward…

Preview
Year
2026
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2611.19304ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

A backdoored language model behaves normally until a trigger phrase appears in its input. Every published method for recovering such a trigger runs the model. We show the trigger is legible in the weights alone: a static statistic reads a fine-tuned checkpoint with no forward pass of the suspect, no data, no labelled population of poisoned models and no prior knowledge that a backdoor exists, and names one of the tokens of the trigger phrase as the single highest-ranked candidate in the vocabulary.