Attacks, Defenses and Testing for Deep Learning

Langue : anglais

Edité par Springer Nature Singapore Jul 2024, 2024

9819704243 / 9789819704248

Vendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, AllemagneBuchWeltWeit Ludwig Meier e.K.

Vendeur avec une évaluation de 5 étoiles

Vendeur AbeBooks depuis 11 janvier 2012

Livre relié

Etat: Neuf

EUR 235,39

EUR 23,00 expédition 
Expédition depuis Allemagne vers Etats-Unis

Quantité disponible : 2 disponibles

Ajouter au panier
Retours gratuits sous 30 jours

A propos de cet article

This item is printed on demand - it takes 3-4 days longer - Neuware -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, wherethe 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. 399 pp. Englisch. …

N° de réf. du vendeur 9789819704248

Titre
Attacks, Defenses and Testing for Deep Learning
Auteur
Jinyin Chen
Éditeur
Springer Nature Singapore Jul 2024
Année de publication
2024
État de l'article
Neu
Reliure
Buch
Langue
anglais
ISBN à 10 chiffres
9819704243
ISBN à 13 chiffres
9789819704248
Dimensions
235x155x35 mm

BuchWeltWeit Ludwig Meier e.K.

Bergisch Gladbach, Allemagne

Vendeur avec une évaluation de 5 étoiles

Vendeur AbeBooks depuis 11 janvier 2012

Frais d'expédition de Allemagne vers Etats-Unis

Article5 à 15 jours ouvrés5 à 15 jours ouvrés
Premier articleEUR 23,00EUR 23,00
Les délais de livraison sont fixés par les vendeurs et varient en fonction du transporteur et du lieu. Les commandes transitant par les douanes peuvent être retardées et les acheteurs sont responsables de tous les droits ou frais associés. Les vendeurs peuvent vous contacter au sujet de frais supplémentaires afin de couvrir toute augmentation des coûts d'expédition de vos articles.

Modes de paiement

  • Visa
  • Mastercard
  • American Express
  • Carte Bleue
  • Apple Pay
  • Google Pay
  • Chèque
  • Paypal
  • Virement bancaire

Profil professionnel du vendeur

BuchWeltWeit Ludwig Meier e.K.

Allemagne