Strengthening deep neural networks : making AI less susceptible to adversarial trickery / (Record no. 65496)
[ view plain ]
000 -LEADER | |
---|---|
fixed length control field | 01307nam a22001817a 4500 |
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
fixed length control field | 200609b2019 ||||| |||| 00| 0 eng d |
020 ## - INTERNATIONAL STANDARD BOOK NUMBER | |
International Standard Book Number | 9789352138739 |
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
Classification number | 006.32 WAR-K |
100 ## - MAIN ENTRY--PERSONAL NAME | |
Personal name | Warr, Katy |
245 ## - TITLE STATEMENT | |
Title | Strengthening deep neural networks : making AI less susceptible to adversarial trickery / |
Statement of responsibility, etc. | Katy Warr |
260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
Place of publication, distribution, etc. | India |
Name of publisher, distributor, etc. | SPD / O'Reilly |
Date of publication, distribution, etc. | 2019 |
300 ## - PHYSICAL DESCRIPTION | |
Extent | 227 p. |
365 ## - TRADE PRICE | |
Price type code | INR |
Price amount | 850.00 |
500 ## - GENERAL NOTE | |
General note | As deep neural networks (DNNs) become increasingly common in real-world applications, the potential to deliberately "fool" them with data that wouldn’t trick a human presents a new attack vector. This practical book examines real-world scenarios where DNNs—the algorithms intrinsic to much of AI—are used daily to process image, audio, and video data.<br/><br/>Author Katy Warr considers attack motivations, the risks posed by this adversarial input, and methods for increasing AI robustness to these attacks. If you’re a data scientist developing DNN algorithms, a security architect interested in how to make AI systems more resilient to attack, or someone fascinated by the differences between artificial and biological perception. |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name as entry element | Neural networks (Computer science) |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name as entry element | Artificial intelligence |
650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
Topical term or geographic name as entry element | Computer networks--Security measures |
952 ## - LOCATION AND ITEM INFORMATION (KOHA) | |
Withdrawn status |
Lost status | Source of classification or shelving scheme | Damaged status | Not for loan | Collection code | Home library | Current library | Shelving location | Date acquired | Total Checkouts | Total Renewals | Full call number | Barcode | Date last seen | Date last checked out | Price effective from | Koha item type |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Dewey Decimal Classification | 003-007 | BITS Pilani Hyderabad | BITS Pilani Hyderabad | General Stack (For lending) | 09/06/2020 | 8 | 2 | 006.32 WAR-K | 41197 | 17/01/2025 | 20/08/2024 | 09/06/2020 | Books |