Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers
Adversarial attacks on machine learning-based classifiers, along with defense mechanisms, have been widely studied in the context of single-label classification problems. In this paper, we shift the attention to multi-label classification, where the availability of domain knowledge on the relationsh...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 12 vom: 23. Dez., Seite 9944-9959
|
|---|
| 1. Verfasser: |
Melacci, Stefano
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Ciravegna, Gabriele,
Sotgiu, Angelo,
Demontis, Ambra,
Biggio, Battista,
Gori, Marco,
Roli, Fabio |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2022
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|