Auditability of subliminal learning is constrained by channel location, with initialization-dependent body channels allowing pre-training screens while vocabulary geometry and conditional body channels evade them.
arXiv preprint arXiv:2009.08576 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.
citing papers explorer
-
Channel Location Constrains the Auditability of Subliminal Learning
Auditability of subliminal learning is constrained by channel location, with initialization-dependent body channels allowing pre-training screens while vocabulary geometry and conditional body channels evade them.
-
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
SalUn uses gradient-based weight saliency to achieve effective machine unlearning of data, classes, or concepts in image classification and generation, narrowing the gap to exact retraining.