Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Feature. (arXiv:2305.01361v1 [cs.CV])

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 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 feature-level …

adversarial attack box disrupt networks neural networks neuron research vulnerable