An analysis of adversarial algorithm techniques in image recognition and their countermeasures
The ability of neural network models to generalise and identify unseen data allows for neural networks to operate outside of what it has been trained on, but makes it vulnerable to data samples altered in human imperceptible ways to produce incorrect predictions. This project aims to experimentally...
Saved in:
Main Author: | Tan, Alastair Song Xin |
---|---|
Other Authors: | Kong Wai-Kin Adams |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/153433 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Challenges and countermeasures for adversarial attacks on deep reinforcement learning
by: Ilahi, Inaam, et al.
Published: (2022) -
A randomized countermeasure against parasitic adversaries in wireless sensor networks
by: Luo, Jun., et al.
Published: (2011) -
Web vulnerabilities and countermeasures
by: Chen, Tiffany Yuhui
Published: (2014) -
Speaker-invariant speech emotion recognition with domain adversarial training
by: Leow, Bryan Xuan Zhen
Published: (2021) -
Architecture and algorithm development for generative adversarial networks
by: Yazici, Yasin
Published: (2020)