Year: 2026
Type: preprint
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 edit yields 79.8% test accuracy, which is 91.2% of the fitted score's gain over chance; tighter edit limits sharply reduce success. Linear guardedness therefore remains a valid guarantee about the current representation, but it is not by itself a tamper-resistance guarantee for an editable open-weight model.
Source: arXiv (Cornell University)
Authors: Sharma, Jai Kumar, Khattar, Vanshaj
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7236701619
