Attacks, Defenses and Testing for Deep Learning Hardback - 2024
by Jinyin Chen
- New
- Hardback
A$377.00
A$15.42
Delivery to USA
Standard delivery: 7 to 12 days
More delivery options
Standard delivery: 7 to 12 days
Ships from Ria Christie Collections (Greater London, United Kingdom)
Details
- Title Attacks, Defenses and Testing for Deep Learning
- Author Jinyin Chen
- Binding Hardback
- Condition New
- Pages 399
- Volumes 1
- Language ENG
- Publisher Springer
- Publication date 2024-06-04
- Illustrated Yes
- Features Illustrated
- Bookseller's Inventory # ria9789819704248_inp
- ISBN 9789819704248 / 9819704243
- Weight 1.68 lbs (0.76 kg)
- Dimensions 9.21 x 6.14 x 0.94 in (23.39 x 15.60 x 2.39 cm)
- Category Computers - General Information
- Quantity available 296
About Ria Christie Collections Greater London, United Kingdom
Biblio member since 2014
Hello We are professional online booksellers. We sell mostly new books and textbooks and we do our best to provide a competitive price. We are based in Greater London, UK. We pride ourselves by providing a good customer service throughout, shipping the items quickly and replying to customer queries promptly. Ria Christie Collections
30 day return guarantee, with full refund including original shipping costs for up to 30 days after delivery if an item arrives misdescribed or damaged.
Reader reviews for Attacks, Defenses and Testing for Deep Learning
Write a review for this book
Important Terms and Guidelines
- Please focus on the book’s content and context. Also, add any personal comments as to how you enjoyed the book. Substantiate your likes and dislikes. You may make comparisons to other books.
- Reviews must be at least 140 characters in length.
- Please do not reveal critical plot elements.
- This is not a help line. Contact customer support if you need help.
Your review must not include:
- Obscenities, discriminatory language, or other insulting language not suitable for public domain
- Advertisements, “spam” content, or references to other products, offers or websites.
- Email addresses, URLs, phone numbers, physical addresses or other contact information.
- Overly critical comments about other reviews or reviewers
- Time-sensitive material (i.e. promotional tours, seminars, lectures, etc.)
- Availability, price, or alternative ordering/shipping information
From the publisher
From the rear cover
This book provides a systematic study on the security of deep learning. With its powerful learning ability, deep learning is widely used in CV, FL, GNN, RL, and other scenarios. However, during the process of application, researchers have revealed that deep learning is vulnerable to malicious attacks, which will lead to unpredictable consequences. Take autonomous driving as an example, there were more than 12 serious autonomous driving accidents in the world in 2018, including Uber, Tesla and other high technological enterprises. Drawing on the reviewed literature, we need to discover vulnerabilities in deep learning through attacks, reinforce its defense, and test model performance to ensure its robustness.
Attacks can be divided into adversarial attacks and poisoning attacks. Adversarial attacks occur during the model testing phase, where the attacker obtains adversarial examples by adding small perturbations. Poisoning attacks occur during the model training phase, where the attacker injects poisoned examples into the training dataset, embedding a backdoor trigger in the trained deep learning model.
An effective defense method is an important guarantee for the application of deep learning. The existing defense methods are divided into three types, including the data modification defense method, model modification defense method, and network add-on method. The data modification defense method performs adversarial defense by fine-tuning the input data. The model modification defense method adjusts the model framework to achieve the effect of defending against attacks. The network add-on method prevents the adversarial examples by training the adversarial example detector.
Testing deep neural networks is an effective method to measure the security and robustness of deep learning models. Through test evaluation, security vulnerabilities and weaknesses in deep neural networks can be identified. By identifying and fixing these vulnerabilities, the security and robustness of the model can be improved.
Our audience includes researchers in the field of deep learning security, as well as software development engineers specializing in deep learning.
