Boosting 3D Adversarial Attacks With Attacking on Frequency

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks in the image domain. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transfe...

Cur síos iomlán

Na minha lista:
Sonraí Bibleagrafaíochta
Main Authors: Binbin Liu, Jinlai Zhang, Jihong Zhu
Formáid: Artigo
Teanga:Inglês
Foilsithe: IEEE 2022-01-01
Sraith:IEEE Access
Ábhair:
3D adversarial attack
neural networks
point clouds
transferability
frequency
Rochtain Ar Líne:https://ieeexplore.ieee.org/document/9765977/
Clibeanna: Cuir Clib Leis
Gan Chlibeanna, Bí ar an gcéad duine leis an taifead seo a chlibeáil!

Míreanna Comhchosúla