Amazon cover image
Image from Amazon.com

Adversarial machine learning

By: Contributor(s): Material type: TextTextPublication details: Cambridge University Press 2019 CambridgeDescription: xiii, 325 p. : ill. Includes bibliographical references and indexISBN:
  • 9781107043466
Subject(s): DDC classification:
  • 006.31 J6A2
Summary: 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. The first book to provide a state-of-the-art review of adversarial machine learning Covers availability and integrity attacks, privacy-preserving mechanisms, near-optimal evasion of classifiers, and future directions for adversarial machine learning Includes in-depth case studies on email spam and network security https://www.cambridge.org/in/universitypress/subjects/computer-science/communications-information-theory-and-security/adversarial-machine-learning?format=HB&isbn=9781107043466
Tags from this library: No tags from this library for this title. Log in to add tags.
Star ratings
    Average rating: 0.0 (0 votes)
Holdings
Item type Current library Item location Collection Shelving location Call number Status Date due Barcode
Books Vikram Sarabhai Library Rack 4-A / Slot 107 (0 Floor, West Wing) Non-fiction General Stacks 006.31 J6A2 (Browse shelf(Opens below)) Available 206926

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.

The first book to provide a state-of-the-art review of adversarial machine learning
Covers availability and integrity attacks, privacy-preserving mechanisms, near-optimal evasion of classifiers, and future directions for adversarial machine learning
Includes in-depth case studies on email spam and network security


https://www.cambridge.org/in/universitypress/subjects/computer-science/communications-information-theory-and-security/adversarial-machine-learning?format=HB&isbn=9781107043466

There are no comments on this title.

to post a comment.