Mgct: a multi-generator collaborative training approach for data-free model stealing
Abstract Model stealing attacks in the Machine Learning as a Service (MLaaS) paradigm face multiple technical challenges, particularly in scenarios lacking training data support. Target models remain vulnerable to reverse engineering and replication under strict environmental constraints. Existing d...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Artigo |
| Sprache: | Inglês |
| Veröffentlicht: |
SpringerOpen
2026-03-01
|
| Schriftenreihe: | Cybersecurity |
| Schlagworte: | |
| Online-Zugang: | https://doi.org/10.1186/s42400-025-00467-1 |
| Tags: |
Keine Tags, Fügen Sie das erste Tag hinzu!
|