Pith. sign in

Privacy risk in machine learning: Analyzing the connection to overfitting

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2024 1

verdicts

REJECT 1

representative citing papers

Intermediate Outputs Are More Sensitive Than You Think

cs.CV · 2024-12-01 · reject · novelty 5.0

A deep network's intermediate layers can be ranked by privacy risk using estimated degrees of freedom and Jacobian rank, which the authors link to membership inference attack success.

citing papers explorer

Showing 1 of 1 citing paper.

  • Intermediate Outputs Are More Sensitive Than You Think cs.CV · 2024-12-01 · reject · none · ref 14

    A deep network's intermediate layers can be ranked by privacy risk using estimated degrees of freedom and Jacobian rank, which the authors link to membership inference attack success.