Strengthening Deep Neural Networks: Making AI Less Susceptible to Adversarial Trickery
Authors: Katy Warr
ISBN-10: 1492044954
ISBN-13: 9781492044956
Edition 版本: 1
Released: 2019-08-13
Print Length 页数: 246 pages
Book Description
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,this book is for you.
Delve into DNNs and discover how they could be tricked by adversarial input
Investigate methods used to generate adversarial input capable of fooling DNNs
Explore real-world scenarios and model the adversarial threat
Evaluate neural network robustness; learn methods to increase resilience of AI systems to adversarial data
Examine some ways in which AI might become better at mimicking human perception in years to come
Preface
1. An Introduction to Fooling Al
1. Introduction
2. Attack Motivations
3. Deep Neural Network(DNN) Fundamentals
4. DNN Processing for lmage,Audio,and Video
ll. Generating Adversarial Input
5. The Principles of Adversarial Input
6. Methods for Generating Adversarial Perturbation
ll. Understanding the Real-World Threat
7. Attack Patterns for Real-World Systems
8. Physical-World Attacks
Ⅳ. Defense
9. Evaluating Model Robustness to Adversarial Inputs
10. Defending Against Adversarial Inputs
11. Future Trends: Toward Robust Al
A. Mathematics Terminology Reference
Index
