• Afhalen na 1 uur in een winkel met voorraad
  • Gratis thuislevering in België vanaf € 30
  • Ruim aanbod met 7 miljoen producten
  • Afhalen na 1 uur in een winkel met voorraad
  • Gratis thuislevering in België vanaf € 30
  • Ruim aanbod met 7 miljoen producten

Backdoor Attacks Against Learning-Based Algorithms

Shaofeng Li, Haojin Zhu, Wen Wu, Shen
Hardcover | Engels | Wireless Networks
€ 158,45
+ 316 punten
Levertermijn 1 à 4 weken
Eenvoudig bestellen
Veilig betalen
Gratis thuislevering vanaf € 30 (via bpost)
Gratis levering in je Standaard Boekhandel

Omschrijving

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.

Specificaties

Betrokkenen

Auteur(s):
Uitgeverij:

Inhoud

Aantal bladzijden:
153
Taal:
Engels
Reeks:

Eigenschappen

Productcode (EAN):
9783031573880
Verschijningsdatum:
30/05/2024
Uitvoering:
Hardcover
Formaat:
Genaaid
Afmetingen:
38 mm x 221 mm
Gewicht:
385 g
Standaard Boekhandel

Alleen bij Standaard Boekhandel

+ 316 punten op je klantenkaart van Standaard Boekhandel
E-BOOK ACTIE

Tot meer dan 50% korting

op een selectie e-books
E-BOOK ACTIE
E-book kortingen
Standaard Boekhandel

Beoordelingen

We publiceren alleen reviews die voldoen aan de voorwaarden voor reviews. Bekijk onze voorwaarden voor reviews.