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.
Sok: Security and privacy in machine learning
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.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Intermediate Outputs Are More Sensitive Than You Think
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.