CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
The EU proposal for a general data protection regulation and the roots of the 'right to be forgotten'
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
GEM bridges trajectory-based unlearning and teacher-guided erasure to create a geometric guidance objective for targeted concept suppression in Rectified Flow models.
citing papers explorer
-
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models
CheckMIABench converts LLMs with intermediate checkpoints into clean MIA testbeds by using pre- and post-checkpoint training data from the same distribution and evaluates published attacks on Pythia and OLMo models while releasing an open-source library.
-
Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
GEM bridges trajectory-based unlearning and teacher-guided erasure to create a geometric guidance objective for targeted concept suppression in Rectified Flow models.