The strength of Nesterov’s accelerated gradient in boosting transferability of stealthy adversarial attacks
Sign Up to like & getrecommendations! Published in 2025 at "PLOS One"
DOI: 10.1371/journal.pone.0337463
Abstract: Deep neural networks have been shown to be highly vulnerable to adversarial examples—inputs crafted to mislead models by adding subtle, human-imperceptible perturbations. Transferability and stealthiness are two crucial metrics for evaluating adversarial attacks. However, these… read more here.
Keywords: black box; transferability; boosting transferability; accelerated gradient ... See more keywords