Código QR (código de barras bidimensional)

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...

תיאור מלא

שמור ב:
Principais autores: Joana Cabral Costa, Tiago Roxo, Hugo Proença, Pedro R. M. Inácio
פורמט: Artigo
שפה:Inglês
יצא לאור: PeerJ Inc. 2026-04-01
סדרה:PeerJ Computer Science
נושאים:
Adversarial attacks
Gray-box
Robustness
Similarity training
Adversarial defense
גישה מקוונת:https://peerj.com/articles/cs-3735.pdf
תגים: הוספת תג
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!

פריטים דומים