Novel defense based on softmax activation transformation
Deep learning is widely used in various fields such as image processing, natural language processing, network mining and so on.However, it is vulnerable to malicious adversarial attacks and many defensive methods have been proposed accordingly.Most defense methods are attack-dependent and require de...
Saved in:
Main Authors: | Jinyin CHEN, Changan WU, Haibin ZHENG |
---|---|
Format: | Article |
Language: | English |
Published: |
POSTS&TELECOM PRESS Co., LTD
2022-04-01
|
Series: | 网络与信息安全学报 |
Subjects: | |
Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2022016 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Survey of optical-based physical domain adversarial attacks and defense
by: CHEN Jinyin, et al.
Published: (2024-04-01) -
Adversarial attacks and defenses in deep learning
by: Ximeng LIU, et al.
Published: (2020-10-01) -
Adversarial patch defense algorithm based on PatchTracker
by: Zhenjie XIAO, et al.
Published: (2024-02-01) -
Survey on adversarial attacks and defenses for object detection
by: Xinxin WANG, et al.
Published: (2023-11-01) -
Adversarial attack and defense on graph neural networks: a survey
by: Jinyin CHEN, et al.
Published: (2021-06-01)