Optimizing membership inference attacks against low self-influence samples by distilled shadow models and inference models
Machine learning models face increasing threats from membership inference attacks, which aim to infer sample membership. Sample membership represents whether or not a particular data sample is included in the training set of a given model and is considered a fundamental form of privacy leakage. Rece...
Bewaard in:
| Hoofdauteurs: | , |
|---|---|
| Formaat: | Artigo |
| Taal: | Inglês |
| Gepubliceerd in: |
PeerJ Inc.
2025-10-01
|
| Reeks: | PeerJ Computer Science |
| Onderwerpen: | |
| Online toegang: | https://peerj.com/articles/cs-3269.pdf |
| Tags: |
Geen labels, Wees de eerste die dit record labelt!
|