LISArD: learning image similarity to defend against gray-box adversarial attacks
State-of-the-art defense mechanisms are typically evaluated in the context of white-box attacks, which is not realistic, as it assumes the attacker can access the gradients of the target network. To protect against this scenario, Adversarial Training (AT) and Adversarial Distillation (AD) include ad...
Gardado en:
| Principais autores: | , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado: |
PeerJ Inc.
2026-04-01
|
| Series: | PeerJ Computer Science |
| Assuntos: | |
| Acceso en liña: | https://peerj.com/articles/cs-3735.pdf |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|