Evaluation of adversarial attacks against deep learning models

As artificial intelligence (AI) has grown in popularity over the years, the application of AI and deep learning models to make our lives easier has become more prevalent which led to the increase in usage and reliance of AI. This provides increased incentives for attackers to trick deep learning mod...

Full description

Saved in:
Bibliographic Details
Main Author: Chua, Wenjun
Other Authors: Zhang Tianwei
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/175064
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-175064
record_format dspace
spelling sg-ntu-dr.10356-1750642024-04-19T15:41:54Z Evaluation of adversarial attacks against deep learning models Chua, Wenjun Zhang Tianwei School of Computer Science and Engineering tianwei.zhang@ntu.edu.sg Computer and Information Science As artificial intelligence (AI) has grown in popularity over the years, the application of AI and deep learning models to make our lives easier has become more prevalent which led to the increase in usage and reliance of AI. This provides increased incentives for attackers to trick deep learning models into generating false results for their benefit, making them more susceptible to adversarial attacks by hackers and threatening the stability and robustness of deep learning models. This report serves to replicate and evaluate various known adversarial attacks against popular deep learning models and evaluate their performance. Experimental results show that while certain defenses exhibit efficacy against specific adversarial attacks, none provides comprehensive protection against all threats. Bachelor's degree 2024-04-19T02:30:34Z 2024-04-19T02:30:34Z 2024 Final Year Project (FYP) Chua, W. (2024). Evaluation of adversarial attacks against deep learning models. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175064 https://hdl.handle.net/10356/175064 en SCSE23-0071 application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
spellingShingle Computer and Information Science
Chua, Wenjun
Evaluation of adversarial attacks against deep learning models
description As artificial intelligence (AI) has grown in popularity over the years, the application of AI and deep learning models to make our lives easier has become more prevalent which led to the increase in usage and reliance of AI. This provides increased incentives for attackers to trick deep learning models into generating false results for their benefit, making them more susceptible to adversarial attacks by hackers and threatening the stability and robustness of deep learning models. This report serves to replicate and evaluate various known adversarial attacks against popular deep learning models and evaluate their performance. Experimental results show that while certain defenses exhibit efficacy against specific adversarial attacks, none provides comprehensive protection against all threats.
author2 Zhang Tianwei
author_facet Zhang Tianwei
Chua, Wenjun
format Final Year Project
author Chua, Wenjun
author_sort Chua, Wenjun
title Evaluation of adversarial attacks against deep learning models
title_short Evaluation of adversarial attacks against deep learning models
title_full Evaluation of adversarial attacks against deep learning models
title_fullStr Evaluation of adversarial attacks against deep learning models
title_full_unstemmed Evaluation of adversarial attacks against deep learning models
title_sort evaluation of adversarial attacks against deep learning models
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/175064
_version_ 1800916222490968064