Restricted Region Based Iterative Gradient Method for Non-Targeted Attack
Neural networks have been widely applied but they are still vulnerable to adversarial examples. More and more defense models have been proposed and they can resist the attacks to the neural networks. In order to generate adversarial examples with good transferability, we propose the restricted regio...
Main Authors: | Zhaoquan Gu, Weixiong Hu, Chuanjing Zhang, Le Wang, Chunsheng Zhu, Zhihong Tian |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8978619/ |
Similar Items
-
Machine learning through cryptographic glasses: combating adversarial attacks by key-based diversified aggregation
by: Olga Taran, et al.
Published: (2020-06-01) -
Partial Retraining Substitute Model for Query-Limited Black-Box Attacks
by: Hosung Park, et al.
Published: (2020-10-01) -
A CMA-ES-Based Adversarial Attack on Black-Box Deep Neural Networks
by: Xiaohui Kuang, et al.
Published: (2019-01-01) -
Timing Black-Box Attacks: Crafting Adversarial Examples through Timing Leaks against DNNs on Embedded Devices
by: Tsunato Nakai, et al.
Published: (2021-07-01) -
Multitask adversarial attack with dispersion amplification
by: Pavlo Haleta, et al.
Published: (2021-09-01)