Adversarial example defense algorithm for MNIST based on image reconstruction
With the popularization of deep learning, more and more attention has been paid to its security issues.The adversarial sample is to add a small disturbance to the original image, which can cause the deep learning model to misclassify the image, which seriously affects the performance of deep learnin...
Saved in:
Main Authors: | Zhongyuan QIN, Zhaoxiang HE, Tao LI, Liquan CHEN |
---|---|
Format: | Article |
Language: | English |
Published: |
POSTS&TELECOM PRESS Co., LTD
2022-02-01
|
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.2021095 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Mape: defending against transferable adversarial attacks using multi-source adversarial perturbations elimination
by: Xinlei Liu, et al.
Published: (2025-01-01) -
Research on structure and defense of adversarial example in deep learning
by: Guanghan DUAN, et al.
Published: (2020-04-01) -
Adversarial attacks and defenses in deep learning
by: Ximeng LIU, et al.
Published: (2020-10-01) -
SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL
by: Thanh Son Phan, et al.
Published: (2024-08-01) -
Adversarial examples defense method based on multi-dimensional feature maps knowledge distillation
by: Baolin QIU, et al.
Published: (2022-04-01)