國立虎尾科技大學 |

Formal Verification of Neural Networks : = Algorithms and Applications.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Formal Verification of Neural Networks :/
Reminder of title:	Algorithms and Applications.
Author:	Khedr, Haitham.
Description:	1 online resource (167 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-08, Section: B.
Contained By:	Dissertations Abstracts International85-08B.
Subject:	Computer engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9798381570830

Formal Verification of Neural Networks : = Algorithms and Applications.
Khedr, Haitham.

Formal Verification of Neural Networks :Algorithms and Applications. - 1 online resource (167 pages)

Source: Dissertations Abstracts International, Volume: 85-08, Section: B.

Thesis (Ph.D.)--University of California, Irvine, 2023.

Includes bibliographical references

Neural networks (NNs) have become the backbone of intelligent systems, with applications ranging from sensing modules to learning-based controllers. Their deployment in safety-critical domains such as healthcare and transportation underscores their significance. However, the fragility of NNs and their potential for dangerous mistakes, whether unintentional or adversarial, necessitates rigorous checks on their behavior. This thesis delves into the Formal Verification of NNs, a process that can provides formal guarantees on their behavior and ensures the reliability and robustness of these systems.The cornerstone of this work is a novel algorithm, PeregriNN, that has advanced the Formal Verification of NNs. This algorithm has been used to verify various NN properties such as Adversarial Robustness, safety of autonomous systems, and in demonstrating the fairness of NNs by innovatively formulating the fairness property into a Formal Verification problem. Further, this thesis explores a new type of activation function that simplifies the formal verification process, albeit at the cost of increased training time. This exploration, coupled with a collaborative effort that led to the proposal of a polynomial approximation method for ReLU NNs to formally verify them, provides valuable insights into the balance between verification ease and computational efficiency. These methods offer promising approaches to the formal verification of neural networks, further enhancing the robustness and reliability of these systems. The thesis also extends the application of these theories and algorithms to the safety of autonomous systems with neural network controllers. This practical application underscores the real-world implications of formal verification in ensuring the safety and reliability of autonomous systems.In summary, this thesis provides a comprehensive understanding of the formal verification of neural networks, underscoring the importance of algorithm development and its real-world applications. The findings from this study contribute significantly to this critical field of study, with implications for the fairness, safety, and robustness of NNs.

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

Mode of access: World Wide Web

ISBN: 9798381570830Subjects--Topical Terms:

569006
Computer engineering.
Subjects--Index Terms:

Neural networks Index Terms--Genre/Form:

554714
Electronic books.

Formal Verification of Neural Networks : = Algorithms and Applications.
LDR:03557ntm a22003977 4500 001 1148341
005 20240924101858.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381570830
035 $a (MiAaPQ)AAI30815286
035 $a AAI30815286
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Khedr, Haitham. $3 1474288
245 1 0 $a Formal Verification of Neural Networks : $b Algorithms and Applications.
264 0 $c 2023
300 $a 1 online resource (167 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: 85-08, Section: B.
500 $a Advisor: Shoukry, Yasser.
502 $a Thesis (Ph.D.)--University of California, Irvine, 2023.
504 $a Includes bibliographical references
520 $a Neural networks (NNs) have become the backbone of intelligent systems, with applications ranging from sensing modules to learning-based controllers. Their deployment in safety-critical domains such as healthcare and transportation underscores their significance. However, the fragility of NNs and their potential for dangerous mistakes, whether unintentional or adversarial, necessitates rigorous checks on their behavior. This thesis delves into the Formal Verification of NNs, a process that can provides formal guarantees on their behavior and ensures the reliability and robustness of these systems.The cornerstone of this work is a novel algorithm, PeregriNN, that has advanced the Formal Verification of NNs. This algorithm has been used to verify various NN properties such as Adversarial Robustness, safety of autonomous systems, and in demonstrating the fairness of NNs by innovatively formulating the fairness property into a Formal Verification problem. Further, this thesis explores a new type of activation function that simplifies the formal verification process, albeit at the cost of increased training time. This exploration, coupled with a collaborative effort that led to the proposal of a polynomial approximation method for ReLU NNs to formally verify them, provides valuable insights into the balance between verification ease and computational efficiency. These methods offer promising approaches to the formal verification of neural networks, further enhancing the robustness and reliability of these systems. The thesis also extends the application of these theories and algorithms to the safety of autonomous systems with neural network controllers. This practical application underscores the real-world implications of formal verification in ensuring the safety and reliability of autonomous systems.In summary, this thesis provides a comprehensive understanding of the formal verification of neural networks, underscoring the importance of algorithm development and its real-world applications. The findings from this study contribute significantly to this critical field of study, with implications for the fairness, safety, and robustness of NNs.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer engineering. $3 569006
650 4 $a Electrical engineering. $3 596380
653 $a Neural networks
653 $a Intelligent systems
653 $a Formal Verification
653 $a Robustness
653 $a Novel algorithm
655 7 $a Electronic books. $2 local $3 554714
690 $a 0464
690 $a 0544
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Irvine. $b Electrical and Computer Engineering. $3 1192604
773 0 $t Dissertations Abstracts International $g 85-08B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30815286 $z click for full text (PQDT)