國立虎尾科技大學 |

Fortifying Robustness : = Unveiling the Intricacies of Training and Inference Vulnerabilities in Centralized and Federated Neural Networks.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Fortifying Robustness :/
Reminder of title:	Unveiling the Intricacies of Training and Inference Vulnerabilities in Centralized and Federated Neural Networks.
Author:	Liu, Guanxiong.
Description:	1 online resource (196 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
Subject:	Electrical engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798380604857

Fortifying Robustness : = Unveiling the Intricacies of Training and Inference Vulnerabilities in Centralized and Federated Neural Networks.
Liu, Guanxiong.

Fortifying Robustness :Unveiling the Intricacies of Training and Inference Vulnerabilities in Centralized and Federated Neural Networks. - 1 online resource (196 pages)

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

Thesis (Ph.D.)--New Jersey Institute of Technology, 2023.

Includes bibliographical references

Neural network (NN) classifiers have gained significant traction in diverse domains such as natural language processing, computer vision, and cybersecurity, owing to their remarkable ability to approximate complex latent distributions from data. Nevertheless, the conventional assumption of an attack-free operating environment has been challenged by the emergence of adversarial examples. These perturbed samples, which are typically imperceptible to human observers, can lead to misclassifications by the NN classifiers. Moreover, recent studies have uncovered the ability of poisoned training data to generate Trojan backdoored classifiers that exhibit misclassification behavior triggered by predefined patterns.In recent years, significant research efforts have been dedicated to uncovering the vulnerabilities of NN classifiers and developing defenses or mitigations against them. However, the existing approaches still fall short of providing mature solutions to address this ever-evolving problem. The widely adopted defense mechanisms against adversarial examples are computationally expensive and impractical for certain real-world applications. Likewise, the practical black-box defense against Trojan backdoors has failed to achieve state-of-the-art performance. More concerning is the limited exploration of these vulnerabilities within the context of cooperative attack or Federated learning, leaving NN classifiers exposed to unknown risks. This dissertation aims to address these critical gaps and refine our understanding of these vulnerabilities. The research conducted within this dissertation encompasses both the attack and defense perspectives, aiming to shed light on future research directions for vulnerabilities in NN classifiers.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380604857Subjects--Topical Terms:

596380
Electrical engineering.
Subjects--Index Terms:

Adversarial attackIndex Terms--Genre/Form:

554714
Electronic books.

Fortifying Robustness : = Unveiling the Intricacies of Training and Inference Vulnerabilities in Centralized and Federated Neural Networks.
LDR:03225ntm a22003977 4500 001 1151979
005 20241125080159.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380604857
035 $a (MiAaPQ)AAI30250497
035 $a AAI30250497
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Liu, Guanxiong. $3 1478842
245 1 0 $a Fortifying Robustness : $b Unveiling the Intricacies of Training and Inference Vulnerabilities in Centralized and Federated Neural Networks.
264 0 $c 2023
300 $a 1 online resource (196 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
500 $a Advisor: Khreishah, Abdallah;Khalil, Issa.
502 $a Thesis (Ph.D.)--New Jersey Institute of Technology, 2023.
504 $a Includes bibliographical references
520 $a Neural network (NN) classifiers have gained significant traction in diverse domains such as natural language processing, computer vision, and cybersecurity, owing to their remarkable ability to approximate complex latent distributions from data. Nevertheless, the conventional assumption of an attack-free operating environment has been challenged by the emergence of adversarial examples. These perturbed samples, which are typically imperceptible to human observers, can lead to misclassifications by the NN classifiers. Moreover, recent studies have uncovered the ability of poisoned training data to generate Trojan backdoored classifiers that exhibit misclassification behavior triggered by predefined patterns.In recent years, significant research efforts have been dedicated to uncovering the vulnerabilities of NN classifiers and developing defenses or mitigations against them. However, the existing approaches still fall short of providing mature solutions to address this ever-evolving problem. The widely adopted defense mechanisms against adversarial examples are computationally expensive and impractical for certain real-world applications. Likewise, the practical black-box defense against Trojan backdoors has failed to achieve state-of-the-art performance. More concerning is the limited exploration of these vulnerabilities within the context of cooperative attack or Federated learning, leaving NN classifiers exposed to unknown risks. This dissertation aims to address these critical gaps and refine our understanding of these vulnerabilities. The research conducted within this dissertation encompasses both the attack and defense perspectives, aiming to shed light on future research directions for vulnerabilities in NN classifiers.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
653 $a Adversarial attack
653 $a Adversarial training
653 $a Federated learning
653 $a Neural network
653 $a Trojan attack
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a New Jersey Institute of Technology. $b Helen and John C. Hartmann Department of Electrical and Computer Engineering. $3 1241234
773 0 $t Dissertations Abstracts International $g 85-04B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30250497 $z click for full text (PQDT)