Generating Hard-Label Black-Box Adversarial Examples for Video Recognition Models

In recent years, video recognition models have witnessed the rapid development of Deep Neural Networks (DNNs). However, these models remain not robust to adversarial examples that are created by adding imperceptible perturbations to clean samples. Recent studies indicate that generating adversarial...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Yulin Jing, Lijun Wu, Kaile Su, Wei Wu, Zhiyuan Li, Qi Deng
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2026-03-01
Edice:	Mathematics
Témata:	adversarial examples perturbations neural networks gradient estimation
On-line přístup:	https://www.mdpi.com/2227-7390/14/6/1016
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!