Library Working Hours During Recess
Monday to Friday	09:00 AM - 07:00 PM
Saturday	09:00 AM - 05:00 PM
Sundays & Holidays	Closed

Patron Checkouts
Patrons	No. of Books Issued	Loan Period	Overdue Charges
Faculty	25	6 months	Nil
Students	10	2 Weeks	Re. 1 Per Book Per Day
Research Scholars	15	30 Days	Nil
Staff	5	30 Days	Nil

Image from Amazon.com

Normal view MARC view ISBD view

Strengthening deep neural networks : making AI less susceptible to adversarial trickery / Katy Warr

By:

Warr, Katy

Material type: Text

TextPublication details: India SPD / O'Reilly 2019Description: 227 pISBN:

9789352138739

Subject(s):

DDC classification:

006.32 WAR-K

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Collection	Shelving location	Call number	Status	Date due	Barcode	Item holds
Books	BITS Pilani Hyderabad	003-007	General Stack (For lending)	006.32 WAR-K (Browse shelf(Opens below))	Available		41197

Total holds: 0

Browsing BITS Pilani Hyderabad shelves, Shelving location: General Stack (For lending), Collection: 003-007 Close shelf browser (Hides shelf browser)

Previous								Next
Previous	006.32 SIV-S Introduction to neural networks using MATLAB 6.0 /	006.32 TAN-H Neural networks : computational models and applications /	006.32 TAN-H Neural networks : computational models and applications /	006.32 WAR-K Strengthening deep neural networks : making AI less susceptible to adversarial trickery /	006.32 WEI-S Deep learning from scratch : building with Python from first principles /	006.33 AGA-D Statistical methods for recommender systems /	006.33 DAR-K Essence of expert systems /	Next

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.

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.

There are no comments on this title.

to post a comment.