all AI news
GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model. (arXiv:2401.06031v2 [cs.CV] UPDATED)
cs.CV updates on arXiv.org arxiv.org
Adversarial generative models, such as Generative Adversarial Networks
(GANs), are widely applied for generating various types of data, i.e., images,
text, and audio. Accordingly, its promising performance has led to the
GAN-based adversarial attack methods in the white-box and black-box attack
scenarios. The importance of transferable black-box attacks lies in their
ability to be effective across different models and settings, more closely
aligning with real-world applications. However, it remains challenging to
retain the performance in terms of transferable adversarial examples …
adversarial arxiv attack methods audio box cs.cv data editing gan gans generative generative adversarial networks generative models gradient images importance networks performance samples text types