Backdoor Attacks against Learning-Based Algorithms

Idioma: inglés

Editorial: Springer, Berlin, Springer Nature Switzerland, Springer, 2024

3031573889 / 9783031573880

Librería: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, AlemaniaBuchWeltWeit Ludwig Meier e.K.

Vendedor de 5 estrellas

Vendedor de IberLibro desde 11 de enero de 2012

Tapa dura

Condición: Nuevo

EUR 160,49

Envío por EUR 23,00 
Se envía de Alemania a Estados Unidos de America

Cantidad disponible: 2 disponibles

Añadir al carrito
Devoluciones gratuitas de 30 días

Descripción del artículo del vendedor

This item is printed on demand - it takes 3-4 days longer - Neuware -This book introduces a new type of data poisoning attack, dubbed, backdoor attack. In backdoor attacks, an attacker can train the model with poisoned data to obtain a model that performs well on a normal input but behaves wrongly with crafted triggers. Backdoor attacks can occur in many scenarios where the training process is not entirely controlled, such as using third-party datasets, third-party platforms for training, or directly calling models provided by third parties. Due to the enormous threat that backdoor attacks pose to model supply chain security, they have received widespread attention from academia and industry. This book focuses on exploiting backdoor attacks in the three types of DNN applications, which are image classification, natural language processing, and federated learning.Based on the observation that DNN models are vulnerable to small perturbations, this book demonstrates that steganography and regularization can be adopted to enhance the invisibility of backdoor triggers. Based on image similarity measurement, this book presents two metrics to quantitatively measure the invisibility of backdoor triggers. The invisible trigger design scheme introduced in this book achieves a balance between the invisibility and the effectiveness of backdoor attacks. In the natural language processing domain, it is difficult to design and insert a general backdoor in a manner imperceptible to humans. Any corruption to the textual data (e.g., misspelled words or randomly inserted trigger words/sentences) must retain context-awareness and readability to human inspectors. This book introduces two novel hidden backdoor attacks, targeting three major natural language processing tasks, including toxic comment detection, neural machine translation, and question answering, depending on whether the targeted NLP platform accepts raw Unicode characters.The emerged distributed training framework, i.e., federated learning, has advantages in preserving users' privacy. It has been widely used in electronic medical applications, however, it also faced threats derived from backdoor attacks. This book presents a novel backdoor detection framework in FL-based e-Health systems. We hope this book can provide insightful lights on understanding the backdoor attacks in different types of learning-based algorithms, including computer vision, natural language processing, and federated learning. The systematic principle in this book also offers valuable guidance on the defense of backdoor attacks against future learning-based algorithms. 153 pp. Englisch.…

N° de ref. del artículo 9783031573880

Título
Backdoor Attacks against Learning-Based Algorithms
Autor
Shaofeng Li
Editorial
Springer, Berlin, Springer Nature Switzerland, Springer
Año de publicación
2024
Estado
Neu
Encuadernación
Buch
Idioma
inglés
ISBN 10
3031573889
ISBN 13
9783031573880
Peso del artículo
368 gramos
Dimensiones
235x155x13 mm

BuchWeltWeit Ludwig Meier e.K.

Bergisch Gladbach, Alemania

Vendedor de 5 estrellas

Vendedor de IberLibro desde 11 de enero de 2012

Tarifas de envío de Alemania a Estados Unidos de America

ArtículoDe 5 a 15 días hábilesDe 5 a 15 días hábiles
Primer artículoEUR 23,00EUR 23,00
Los plazos de entrega los establecen los vendedores y varían según el transportista y la ubicación. Los pedidos que pasan por la aduana pueden sufrir retrasos y los compradores son responsables de los aranceles o tarifas asociadas. Los vendedores pueden ponerse en contacto con usted en relación con cargos adicionales para cubrir cualquier aumento en los costes de envío de los artículos.

Métodos de pago

  • Visa
  • Mastercard
  • American Express
  • Carte Bleue
  • Apple Pay
  • Google Pay
  • Cheque
  • Giro bancario
  • PayPal

Información empresarial del vendedor

BuchWeltWeit Ludwig Meier e.K.

Alemania

BuchWeltWeit Inh. Ludwig Meier e.K.
Inhaber: Ludwig Meier
De-Gasperi-Str. 8
51469 Bergisch Gladbach
Deutschland

Tel.: +49(0)22028659300
Fax: +49(0)22028659301
E-Mail: info@buchweltweit.de

Registergericht: Amtsgericht Köln
Registernummer: HRA 28253

Umsatzsteuer-Identifikationsnummer: DE815259907

Wir sind zur Teilnahme an einem Streitbeilegungsverfahren vor einer Verbraucherschlichtungsstelle weder verpflichtet noch bereit.