PDLRecover removes the influence of detected malicious or dropped clients from a decentralized model by approximating their missing gradient updates with secret-shared L-BFGS Hessian-vector products.
Membership inference attacks against machine learning models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
PDLRecover: Privacy-preserving Decentralized Model Recovery with Machine Unlearning
PDLRecover removes the influence of detected malicious or dropped clients from a decentralized model by approximating their missing gradient updates with secret-shared L-BFGS Hessian-vector products.