Comparison of SI-NI-FGSM and SI+Ours.

<p>(a) Attack success rates of different model combinations with increasing steps, attacks are launched from ResNet-18 and transferred to four target models: ResNet-18 (white-box), ResNet-34, ResNet-50, and ResNet-101 (black-box settings); (b) Attack success rates of different models, the sour...

Πλήρης περιγραφή

Αποθηκεύτηκε σε:

Λεπτομέρειες βιβλιογραφικής εγγραφής
Κύριος συγγραφέας:	Chen Lin (95910) (author)
Άλλοι συγγραφείς:	Sheng Long (14795824) (author)
Έκδοση:	2025
Θέματα:	Neuroscience Biological Sciences not elsewhere classified Information Systems not elsewhere classified two crucial metrics nesterov &# 8217 natural data distribution introduces nesterov ’ goals often conflict generation process toward extensive experiments demonstrate deep neural networks achieving stealthy attacks imperceptible perturbations tend evaluating adversarial attacks div >< p diffusion mechanism guides imperceptible adversarial examples imperceptible perturbations adversarial attacks box attacks strong acceleration size strategy perform poorly novel framework mislead models highly vulnerable generalization capabilities art methods adding subtle adaptive step accelerated gradient
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!

Περιγραφή
Περίληψη:	<p>(a) Attack success rates of different model combinations with increasing steps, attacks are launched from ResNet-18 and transferred to four target models: ResNet-18 (white-box), ResNet-34, ResNet-50, and ResNet-101 (black-box settings); (b) Attack success rates of different models, the source model is ResNet-18.</p>

Comparison of SI-NI-FGSM and SI+Ours.

Παρόμοια τεκμήρια