แจ้งเอกสารไม่ครบถ้วน, ไม่ตรงกับชื่อเรื่อง หรือมีข้อผิดพลาดเกี่ยวกับเอกสาร ติดต่อที่นี่ ==>
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
หากไม่มีอีเมลผู้รับให้กรอก thailis-noc@uni.net.th
Kumar, Shailender. A comprehensive review of adversarial learning and impact of unsharing weights across classes. (). King Mongkut's University of Technology North Bangkok. Central Library. : , 2021.
A comprehensive review of adversarial learning and impact of unsharing weights across classes
Name: Vignesh, S
Organization :
Delhi Technological University Computer Engineering
Email :
s.vignesh_2k17co284@dtu.ac.in
Name: Bhawna
Organization :
Delhi Technological University Computer Engineering
Email :
bhawna11ias@gmail.com
Name: Anand, Shubham
Organization :
Delhi Technological University Computer Engineering
Email :
s0.alively@gmail.com
Name: Kumar, Shailender
Organization :
Delhi Technological University Computer Engineering
Email :
shailenderkumar@dce.ac.in
LCSH:
Machine learning
LCSH:
Artificial intelligence
Abstract:
It is evident from recent developments that deep
learning has the potential to be a fundamental part in almost
every new technology that comes in the future. Deep learning
models have performed exceedingly well on standard image
classification problems, but their performance drops drastically
when presented with adversarial inputs that are created by
adding specific small perturbations to the original image. This
paper will be divided into two sections. The first section will
be a complete review of the existing research in this field. We
will provide the reader with the basic concepts of adversarial
learning and a broad classification of various adversarial attacks
and defenses. In the second section, we propose an ensemble
model with max voting and test the impact of adversarial attacks
by converting the 10-class problem over MNIST images into 10
binary classification problems. Each weight in the middle layers
of a multi-class neural network is shared across all the output
classes of the model. We call them the shared weights of the
network. Our proposed model consists of no shared weights,
shows a slight improve in accuracy against adversarial samples
and can detect out-of-domain inputs.
King Mongkut's University of Technology North Bangkok. Central Library
Address:
BANGKOK
Email:
library@kmutnb.ac.th
Created:
2021
Modified:
2024-05-31
Issued:
2024-05-31
บทความ/Article
application/pdf
BibliograpyCitation :
In IEEE Computer Society. 2021 Fourth International Conference on Computational Intelligence and Communication Technologies (CCICT 2021) (pp.1-8). Los Alamitos, CA : IEEE Computer Society
eng
©copyrights King Mongkut's University of Technology North Bangkok
RightsAccess:
ใช้เวลา
0.024162 วินาที
Vignesh, S
| Title | Contributor | Type |
|---|---|---|
| A comprehensive review of adversarial learning and impact of unsharing weights across classes
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Vignesh, S;Bhawna;Anand, Shubham;Kumar, Shailender | บทความ/Article |
Bhawna
| Title | Contributor | Type |
|---|---|---|
| A comprehensive review of adversarial learning and impact of unsharing weights across classes
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Vignesh, S;Bhawna;Anand, Shubham;Kumar, Shailender | บทความ/Article |
Anand, Shubham
| Title | Contributor | Type |
|---|---|---|
| A comprehensive review of adversarial learning and impact of unsharing weights across classes
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Vignesh, S;Bhawna;Anand, Shubham;Kumar, Shailender | บทความ/Article |
Kumar, Shailender
| Title | Contributor | Type |
|---|---|---|
| A brief survey of detecting spam techniques : Twitter and email
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Kumar, Shailender;Gupta, Shweta | บทความ/Article | |
| A comprehensive review of adversarial learning and impact of unsharing weights across classes
มหาวิทยาลัยเทคโนโลยีพระจอมเกล้าพระนครเหนือ Vignesh, S;Bhawna;Anand, Shubham;Kumar, Shailender | บทความ/Article |