Newshot

A Rank-One Bypass of Fixed Linear Erasure

Summary

arXiv:2611.23880v1 Announce Type: new Abstract: Linear concept erasure can make a target unreadable to a specified family of linear classifiers applied to a model's current internal features. In an open-weight release, however, an attacker can modify the layers that produce those features. We study a fixed affine erasure layer whose upstream model is allowed to change. If the layer transmits even one direction visible to an allowed downstream classifier, the attacker can write a target score into that direction and carry it through the layer. We show that this condition is also necessary, and that for a nonconstant linear target score the required change is a rank-one affine update. Across six CIFAR-10 class-pair tasks, the route restores nearly all pre-erasure target performance and can leave a deployed benign linear head's scores unchanged to numerical tolerance. We then price the attack: with eight target labels and 2,000 unlabelled calibration examples, a 10% mean relative feature…

This source only provides a headline — there is no body to show. Use “Read the original” below to read it at the source.

Published by arXiv cs.LG
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗