Cryptography techniques to defend neural networks from adversarial attacks
As the field of artificial intelligence proceeds to advance, the security and strength of neural network against adversarial attacks have resulted in critical area of concern. This academic research report aims to examine current defense mechanism and proposed plan of cryptographic strategies to sec...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/175454 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-175454 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1754542024-04-26T15:45:27Z Cryptography techniques to defend neural networks from adversarial attacks Tan, Hong Meng Anupam Chattopadhyay School of Computer Science and Engineering anupam@ntu.edu.sg Computer and Information Science Neural network Cryptography Machine learning Encryption As the field of artificial intelligence proceeds to advance, the security and strength of neural network against adversarial attacks have resulted in critical area of concern. This academic research report aims to examine current defense mechanism and proposed plan of cryptographic strategies to secure neural network against such risk and threats. We go deep into the complexities of adversarial attacks, emphasizing how vulnerabilities in neural networks can be exploited and abused, and following recommendations for model accuracy and consistent quality. We examine various cryptographic techniques often used for safe data transport, evaluating their good sense as a defense against malicious attacks. The primary goal is to determine if combining encryption techniques may increase the neural organization models’ resistance to adversarial control. Through this research and examination, we aim to provide a deep understanding of the threats that is posed by adversarial attacks, underline the necessity of broader security norms and support ongoing efforts to strengthen neural networks. The discoveries from this research about are necessary to contribute to the creation of more secure and versatile neural networks, in this manner cultivating increased trust and steadiness of the application in artificial intelligence. Bachelor's degree 2024-04-24T05:30:13Z 2024-04-24T05:30:13Z 2024 Final Year Project (FYP) Tan, H. M. (2024). Cryptography techniques to defend neural networks from adversarial attacks. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/175454 https://hdl.handle.net/10356/175454 en SCSE23-0248 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 Neural network Cryptography Machine learning Encryption |
spellingShingle |
Computer and Information Science Neural network Cryptography Machine learning Encryption Tan, Hong Meng Cryptography techniques to defend neural networks from adversarial attacks |
description |
As the field of artificial intelligence proceeds to advance, the security and strength of neural network against adversarial attacks have resulted in critical area of concern. This academic research report aims to examine current defense mechanism and proposed plan of cryptographic strategies to secure neural network against such risk and threats. We go deep into the complexities of adversarial attacks, emphasizing how vulnerabilities in neural networks can be exploited and abused, and following recommendations for model accuracy and consistent quality. We examine various cryptographic techniques often used for safe data transport, evaluating their good sense as a defense against
malicious attacks. The primary goal is to determine if combining encryption techniques may increase the neural organization models’ resistance to adversarial control. Through this research and examination, we aim to provide a deep understanding of the threats that is posed by adversarial attacks, underline the necessity of broader security norms and support ongoing efforts to strengthen neural networks. The discoveries from this research about are necessary to contribute to the creation of more secure and versatile neural networks, in this manner cultivating increased trust and steadiness of the application in artificial intelligence. |
author2 |
Anupam Chattopadhyay |
author_facet |
Anupam Chattopadhyay Tan, Hong Meng |
format |
Final Year Project |
author |
Tan, Hong Meng |
author_sort |
Tan, Hong Meng |
title |
Cryptography techniques to defend neural networks from adversarial attacks |
title_short |
Cryptography techniques to defend neural networks from adversarial attacks |
title_full |
Cryptography techniques to defend neural networks from adversarial attacks |
title_fullStr |
Cryptography techniques to defend neural networks from adversarial attacks |
title_full_unstemmed |
Cryptography techniques to defend neural networks from adversarial attacks |
title_sort |
cryptography techniques to defend neural networks from adversarial attacks |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/175454 |
_version_ |
1800916342307553280 |