MADE is a training-set-only graph backdoor defense combining homophily-based poisoned-sample isolation with masked unlearning to drive attack success rate to near zero while keeping accuracy high.
Svd-gcn: A simpli- fied graph convolution paradigm for recommendation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MADE: Graph Backdoor Defense with Masked Unlearning
MADE is a training-set-only graph backdoor defense combining homophily-based poisoned-sample isolation with masked unlearning to drive attack success rate to near zero while keeping accuracy high.