Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/153433
Title: An analysis of adversarial algorithm techniques in image recognition and their countermeasures
Authors: Tan, Alastair Song Xin
Keywords: Engineering::Computer science and engineering
Issue Date: 2021
Publisher: Nanyang Technological University
Source: Tan, A. S. X. (2021). An analysis of adversarial algorithm techniques in image recognition and their countermeasures. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/153433
Abstract: 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 test some adversarial algorithms used to fool neural networks, and examine some defensive techniques used to mitigate or prevent such attacks. The MNIST digit dataset, Tensorflow and the Cleverhans Library were used to collect the results required, and it was identified that dropping out neurons and adversarial training not only provided some level of protection against basic adversarial attacks, but improved a model’s capability to generalise and identify unseen, non-adversarial samples.
URI: https://hdl.handle.net/10356/153433
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Final Year Report Final.pdf
  Restricted Access
6.88 MBAdobe PDFView/Open

Page view(s)

80
Updated on May 16, 2022

Download(s)

13
Updated on May 16, 2022

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.