Bis zu 50 % günstiger als neu 3 Jahre rebuy Garantie Professionelles Refurbishment

Backdoor Attacks against Learning-Based Algorithms

Derzeit nicht verfügbar

Handgeprüfte Gebrauchtware

Bis zu 50 % günstiger als neu

Der Umwelt zuliebe

Backdoor Attacks against Learning-Based Algorithms

Shaofeng Li, Haojin Zhu, Wen Wu, Xuemin (Sherman) Shen (Gebundene Ausgabe, Englisch)

Keine Bewertungen vorhanden

Optischer Zustand

Beschreibung

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. Weniger zeigen

Dieses Produkt haben wir gerade leider nicht auf Lager.

ab 28,99 €

Derzeit nicht verfügbar

Handgeprüfte Gebrauchtware

Bis zu 50 % günstiger als neu

Der Umwelt zuliebe

Produktinformationen

Technische Daten

Erscheinungsdatum

30.05.2024

Sprache

Englisch

EAN

9783031573880

Herausgeber

Springer International Publishing

Serien- oder Bandtitel

Wireless Networks

Sonderedition

Nein

Autor

Shaofeng Li, Haojin Zhu, Wen Wu, Xuemin (Sherman) Shen

Seitenanzahl

153

Auflage

2024

Einbandart

Gebundene Ausgabe

Schlagwörter

Deep neural networks, Image classification, Natural language processing, Federated learning, Adversarial attacks, Backdoor attacks, Image steganography, Image similarity, Homograph attacks, Text generation, Language models, e-Health, Coalitional game, Shapley value

Thema-Inhalt

UKN - Netzwerk-Hardware TJKW - Drahtlostechnologie UYQM - Maschinelles Lernen

Höhe

235 mm

Breite

15.5 cm

Hersteller: Springer, Europaplatz 3, Heidelberg, Deutschland, 69115, ProductSafety@springernature.com, Springer Nature Customer Service Center GmbH

Warnhinweise und Sicherheitsinformationen

Informationen nach EU Data Act

Bewertungen

-.-

Leider noch keine Bewertungen

Sicher bei rebuy kaufen

Sehr Gut, 4.52/5.00

Aus 200.000+ Bewertungen

Schreib die erste Bewertung für dieses Produkt!

Wenn du eine Bewertung für dieses Produkt schreibst, hilfst du allen Kund:innen, die noch überlegen, ob sie das Produkt kaufen wollen. Vielen Dank, dass du mitmachst!