Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature. (arXiv:2305.01361v2 [cs.CV] UPDATED)

Recent research has shown that Deep Neural Networks (DNNs) are highly
vulnerable to adversarial samples, which are highly transferable and can be
used to attack other unknown black-box models. To improve the transferability
of adversarial samples, several feature-based adversarial attack methods have
been proposed to disrupt neuron activation in the middle layers. However,
current state-of-the-art feature-based attack methods typically require
additional computation costs for estimating the importance of neurons. To
address this challenge, we propose a Singular Value Decomposition (SVD)-based …

arxiv attack methods boosting box feature networks neural networks neuron research vulnerable