@article{
cyberey2026whitebox,
title={White-Box Sensitivity Auditing with Steering Vectors},
author={Hannah Cyberey and Yangfeng Ji and David Evans},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=EfinGGyQRz},
note={}
}