To access this element change to forms mode OFF
Grant Award View - GA28409-V4
Defense against adversarial attacks on deep learning in computer vision
GA ID:
GA28409-V4
Agency:
Australian Research Council
Approval Date:
27-Nov-2018
Variation Publish Date:
14-Mar-2023
Variation Date:
14-Mar-2023
Category:
Science, Technology, Engineering and Mathematics (STEM) Research
Grant Term:
1-Jan-2019 to 31-Dec-2022
Value (AUD):
$426,000.00
(GST inclusive where applicable)
Varies:
GA28409
- Defense against adversarial attacks on deep learning in computer vision
One-off/Ad hoc:
No
Aggregate Grant Award:
No
PBS Program Name:
ARC 18/19 Discovery
Grant Program:
Discovery Projects
Grant Activity:
Defense against adversarial attacks on deep learning in computer vision
Purpose:
Computer vision applications rely heavily on deep learning, which is highly vulnerable to being fooled by adding subtle perturbations to object/image textures that are imperceptible to humans. This project aims to develop defense mechanisms to detect and remove adversarial patterns from the input images. The project expects to advance knowledge in understanding the vulnerabilities of deep learning, and to design deep learning architectures that are inherently robust. The outcomes of this project will increase the security and reliability of computer vision by detecting, reporting and nullifying such attacks and will benefit the general public and industry on many fronts.
GO ID:
GO Title:
Discovery Projects commencing in 2019
Internal Reference ID:
DP19 Round 1
Selection Process:
Targeted or Restricted Competitive
Confidentiality - Contract:
No
Confidentiality - Outputs:
No
Grant Recipient Details
Recipient Name:
The University of Western Australia
Recipient ABN:
37 882 817 280
Grant Recipient Location
Suburb:
NEDLANDS
Town/City:
NEDLANDS
Postcode:
6009
State/Territory:
WA
Country:
AUSTRALIA
Grant Delivery Location
State/Territory:
WA
Postcode:
6009
Country:
AUSTRALIA