menu

Adversarial Machine Learning
by Anthony D. Joseph and Blaine Nelson and Benjamin I. P. Rubinstein




Overview -
Written by leading researchers, this complete introduction brings together all the theory and tools needed for building robust machine learning in adversarial environments. Discover how machine learning systems can adapt when an adversary actively poisons data to manipulate statistical inference, learn the latest practical techniques for investigating system security and performing robust data analysis, and gain insight into new approaches for designing effective countermeasures against the latest wave of cyber-attacks. Privacy-preserving mechanisms and the near-optimal evasion of classifiers are discussed in detail, and in-depth case studies on email spam and network security highlight successful attacks on traditional machine learning algorithms. Providing a thorough overview of the current state of the art in the field, and possible future directions, this groundbreaking work is essential reading for researchers, practitioners and students in computer security and machine learning, and those wanting to learn about the next stage of the cybersecurity arms race.

  Read Full Product Description
 
local_shippingFor Delivery
In Stock.
This item is Non-Returnable.
FREE Shipping for Club Members help
 
storeBuy Online Pickup At Store
search store by zipcode

 
 
New & Used Marketplace 9 copies from $70.63
 
 
 

More About Adversarial Machine Learning by Anthony D. Joseph; Blaine Nelson; Benjamin I. P. Rubinstein

 
 
 

Overview

Written by leading researchers, this complete introduction brings together all the theory and tools needed for building robust machine learning in adversarial environments. Discover how machine learning systems can adapt when an adversary actively poisons data to manipulate statistical inference, learn the latest practical techniques for investigating system security and performing robust data analysis, and gain insight into new approaches for designing effective countermeasures against the latest wave of cyber-attacks. Privacy-preserving mechanisms and the near-optimal evasion of classifiers are discussed in detail, and in-depth case studies on email spam and network security highlight successful attacks on traditional machine learning algorithms. Providing a thorough overview of the current state of the art in the field, and possible future directions, this groundbreaking work is essential reading for researchers, practitioners and students in computer security and machine learning, and those wanting to learn about the next stage of the cybersecurity arms race.


This item is Non-Returnable.

 

Details

  • ISBN-13: 9781107043466
  • ISBN-10: 1107043468
  • Publisher: Cambridge University Press
  • Publish Date: April 2019
  • Page Count: 338
  • Dimensions: 9.9 x 9.5 x 0.8 inches
  • Shipping Weight: 1.8 pounds


Related Categories

 

BAM Customer Reviews