Cargando…
Strengthening Deep Neural Networks : Making AI Less Susceptible to Adversarial Trickery /
As Deep Neural Networks (DNNs) become increasingly common in real-world applications, the potential to "fool" them presents a new attack vector. In this book, author Katy Warr examines the security implications of how DNNs interpret audio and images very differently to humans. You'll...
| Clasificación: | Libro Electrónico |
|---|---|
| Autor principal: | |
| Autor Corporativo: | |
| Formato: | Electrónico eBook |
| Idioma: | Inglés |
| Publicado: |
Sebastopol :
O'Reilly Media, Incorporated,
2019.
|
| Edición: | First edition. |
| Temas: | |
| Acceso en línea: | Texto completo (Requiere registro previo con correo institucional) |
MARC
| LEADER | 00000cam a2200000 i 4500 | ||
|---|---|---|---|
| 001 | OR_on1099922726 | ||
| 003 | OCoLC | ||
| 005 | 20231017213018.0 | ||
| 006 | m o d | ||
| 007 | cr cnu|||||||| | ||
| 008 | 190306t20192019cau ob 001 0 eng | ||
| 040 | |a AU@ |b eng |e rda |e pn |c AU@ |d C6I |d N$T |d TEFOD |d OCLCF |d YDXIT |d UKAHL |d OCLCQ |d EBLCP |d YDX |d VT2 |d OCLCQ |d OCLCO |d NZAUC |d OCLCQ | ||
| 015 | |a GBB9D0588 |2 bnb | ||
| 016 | 7 | |a 019483782 |2 Uk | |
| 019 | |a 1110047486 |a 1110485751 |a 1140487239 |a 1235833501 |a 1240531978 |a 1244447880 | ||
| 020 | |a 9781492044925 |q (electronic book) | ||
| 020 | |a 149204492X |q (electronic book) | ||
| 020 | |a 9781492044901 |q (electronic book) | ||
| 020 | |a 1492044903 |q (electronic book) | ||
| 020 | |z 9781492044956 | ||
| 020 | |z 1492044954 | ||
| 024 | 8 | |a 9781492044949 | |
| 029 | 0 | |a AU@ |b 000065126563 | |
| 035 | |a (OCoLC)1099922726 |z (OCoLC)1110047486 |z (OCoLC)1110485751 |z (OCoLC)1140487239 |z (OCoLC)1235833501 |z (OCoLC)1240531978 |z (OCoLC)1244447880 | ||
| 037 | |a 0EE71892-02D6-4954-98C4-A9343AA1B79F |b OverDrive, Inc. |n http://www.overdrive.com | ||
| 050 | 4 | |a QA76.87 |b .W37 2019 | |
| 082 | 0 | 4 | |a 006.32 |2 23 |
| 049 | |a UAMI | ||
| 100 | 1 | |a Warr, Katy, |e author. | |
| 245 | 1 | 0 | |a Strengthening Deep Neural Networks : |b Making AI Less Susceptible to Adversarial Trickery / |c Warr, Katy. |
| 250 | |a First edition. | ||
| 264 | 1 | |a Sebastopol : |b O'Reilly Media, Incorporated, |c 2019. | |
| 264 | 4 | |c ©2019 | |
| 300 | |a 1 online resource (250 pages) | ||
| 336 | |a text |b txt |2 rdacontent | ||
| 337 | |a computer |b c |2 rdamedia | ||
| 338 | |a online resource |b cr |2 rdacarrier | ||
| 347 | |a text file | ||
| 504 | |a Includes bibliographical references and index. | ||
| 520 | |a As Deep Neural Networks (DNNs) become increasingly common in real-world applications, the potential to "fool" them presents a new attack vector. In this book, author Katy Warr examines the security implications of how DNNs interpret audio and images very differently to humans. You'll learn about the motivations attackers have for exploiting flaws in DNN algorithms and how to assess the threat to systems incorporating neural network technology. Through practical code examples, this book shows you how DNNs can be fooled and demonstrates the ways they can be hardened against trickery. Learn the basic principles of how DNNs "think" and why this differs from our human understanding of the world Understand adversarial motivations for fooling DNNs and the threat posed to real-world systems Explore approaches for making software systems that incorporate DNNs less susceptible to trickery Peer into the future of Artificial Neural Networks to learn how these algorithms may evolve to become more robust | ||
| 542 | |f Copyright © 2019 Katy Warr | ||
| 550 | |a Made available through: Safari, an O'Reilly Media Company. | ||
| 588 | 0 | |a Online resource; title from digital title page (viewed on September 03, 2019). | |
| 505 | 0 | |a Part 1. An introduction to fooling AI. Introduction -- Attack motivations -- Deep neural network (DNN) fundamentals -- DNN processing for image, audio, and video -- Part 2. Generating adversarial input. The principles of adversarial input -- Methods for generating adversarial perturbation -- Part 3. Understanding the real-world threat. Attack patterns for real-world systems -- Physical-world attacks -- Part 4. Defense. Evaluating model robustness to adversarial inputs -- Defending against adversarial inputs -- Future trends : toward robust AI -- Mathematics terminology reference. | |
| 590 | |a O'Reilly |b O'Reilly Online Learning: Academic/Public Library Edition | ||
| 650 | 0 | |a Neural networks (Computer science) | |
| 650 | 6 | |a Réseaux neuronaux (Informatique) | |
| 650 | 7 | |a Neural networks (Computer science) |2 fast |0 (OCoLC)fst01036260 | |
| 710 | 2 | |a Safari, an O'Reilly Media Company. | |
| 776 | 0 | 8 | |i Print version: |a Warr, Katy. |t Strengthening Deep Neural Networks : Making AI Less Susceptible to Adversarial Trickery. |d Sebastopol : O'Reilly Media, Incorporated, ©2019 |z 9781492044956 |
| 856 | 4 | 0 | |u https://learning.oreilly.com/library/view/~/9781492044949/?ar |z Texto completo (Requiere registro previo con correo institucional) |
| 938 | |a Askews and Holts Library Services |b ASKH |n AH36527706 | ||
| 938 | |a Askews and Holts Library Services |b ASKH |n AH36467803 | ||
| 938 | |a ProQuest Ebook Central |b EBLB |n EBL5833993 | ||
| 938 | |a EBSCOhost |b EBSC |n 2183306 | ||
| 938 | |a YBP Library Services |b YANK |n 16368347 | ||
| 994 | |a 92 |b IZTAP | ||