Adversarial Sparse Teacher: Defense Against Distillation-Based Model Stealing Attacks Using Adversarial Examples
We introduce Adversarial Sparse Teacher (AST), a robust defense method against distillation-based model stealing attacks. Our approach trains a teacher model using adversarial examples to produce sparse logit responses and increase the entropy of the output distribution. Typically, a model generates...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Artigo |
| Sprache: | Inglês |
| Veröffentlicht: |
IEEE
2025-01-01
|
| Schriftenreihe: | IEEE Access |
| Schlagworte: | |
| Online-Zugang: | https://ieeexplore.ieee.org/document/11014106/ |
| Tags: |
Keine Tags, Fügen Sie das erste Tag hinzu!
|