Anthony D Joseph, Blaine Nelson, Benjamin I P Rubinstein, J D Tygar

Adversarial Machine Learning

Mitarbeit:Joseph, Anthony D.; Rubinstein, Benjamin I. P.; Nelson, Blaine

• Gebundenes Buch

Produktbeschreibung

Combining essential theory and practical techniques for analysing system security, and building robust machine learning in adversarial environments, as well as including case studies on email spam and network security, this complete introduction is an invaluable resource for researchers, practitioners and students in computer security and machine learning.

Produktdetails

• Verlag: Cambridge University Press
• Seitenzahl: 338
• Erscheinungstermin: 21. Februar 2019
• Englisch
• Abmessung: 254mm x 177mm x 25mm
• Gewicht: 834g
• ISBN-13: 9781107043466
• ISBN-10: 1107043468
• Artikelnr.: 48095438

Autorenporträt

Anthony D. Joseph is a Chancellor's Professor in the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. He was formerly the Director of Intel Labs Berkeley.

Inhaltsangabe

Part I. Overview of Adversarial Machine Learning: 1. Introduction; 2. Background and notation; 3. A framework for secure learning; Part II. Causative Attacks on Machine Learning: 4. Attacking a hypersphere learner; 5. Availability attack case study: SpamBayes; 6. Integrity attack case study: PCA detector; Part III. Exploratory Attacks on Machine Learning: 7. Privacy-preserving mechanisms for SVM learning; 8. Near-optimal evasion of classifiers; Part IV. Future Directions in Adversarial Machine Learning: 9. Adversarial machine learning challenges.

Rezensionen

'Data Science practitioners tend to be unaware of how easy it is for adversaries to manipulate and misuse adaptive machine learning systems. This book demonstrates the severity of the problem by providing a taxonomy of attacks and studies of adversarial learning. It analyzes older attacks as well as recently discovered surprising weaknesses in deep learning systems. A variety of defenses are discussed for different learning systems and attack types that could help researchers and developers design systems that are more robust to attacks.' Richard Lippmann, Lincoln Laboratory, Massachusetts Institute of Technology