- Main
- Computers - Computer Science
- Strengthening Deep Neural Networks:...
Strengthening Deep Neural Networks: Making AI Less Susceptible to Adversarial Trickery
Katy Warr¿Qué tanto le ha gustado este libro?
¿De qué calidad es el archivo descargado?
Descargue el libro para evaluar su calidad
¿Cuál es la calidad de los archivos descargados?
As deep neural networks (DNNs) become increasingly common in real-world applications, the potential to deliberately "fool" them with data that wouldn’t trick a human presents a new attack vector. This practical book examines real-world scenarios where DNNs—the algorithms intrinsic to much of AI—are used daily to process image, audio, and video data.
Author Katy Warr considers attack motivations, the risks posed by this adversarial input, and methods for increasing AI robustness to these attacks. If you’re a data scientist developing DNN algorithms, a security architect interested in how to make AI systems more resilient to attack, or someone fascinated by the differences between artificial and biological perception, this book is for you.
• Delve into DNNs and discover how they could be tricked by adversarial input
• Investigate methods used to generate adversarial input capable of fooling DNNs
• Explore real-world scenarios and model the adversarial threat
• Evaluate neural network robustness; learn methods to increase resilience of AI systems to adversarial data
• Examine some ways in which AI might become better at mimicking human perception in years to come
Author Katy Warr considers attack motivations, the risks posed by this adversarial input, and methods for increasing AI robustness to these attacks. If you’re a data scientist developing DNN algorithms, a security architect interested in how to make AI systems more resilient to attack, or someone fascinated by the differences between artificial and biological perception, this book is for you.
• Delve into DNNs and discover how they could be tricked by adversarial input
• Investigate methods used to generate adversarial input capable of fooling DNNs
• Explore real-world scenarios and model the adversarial threat
• Evaluate neural network robustness; learn methods to increase resilience of AI systems to adversarial data
• Examine some ways in which AI might become better at mimicking human perception in years to come
Categorías:
Año:
2019
Edición:
1
Editorial:
O’Reilly Media
Idioma:
english
Páginas:
246
ISBN 10:
1492044954
ISBN 13:
9781492044956
Archivo:
PDF, 32.55 MB
Sus etiquetas:
IPFS:
CID , CID Blake2b
english, 2019
Leer en línea
- Descargar
- pdf 32.55 MB Current page
- Checking other formats...
- Convertir a
- Desbloquea la conversión de archivos de más de 8 mbPremium
¿Quieres añadir una librería? Contáctanos a través de support@z-lib.do
El archivo se enviará a su dirección de correo electrónico durante el transcurso de 1-5 minutos.
El archivo será enviado a tu cuenta de Telegram durante 1-5 minutos.
Atención: Asegúrate de haber vinculado tu cuenta al bot Z-Library de Telegram.
El archivo será enviado a tu dispositivo Kindle durante 1-5 minutos.
Nota: Ud. debe verificar cada libro que desea enviar a su Kindle. Revise su correo electrónico y encuentre un mensaje de verificación de Amazon Kindle Support.
Conversión a en curso
La conversión a ha fallado
Beneficios del estado Premium
- Envía a dispositivos de lectura
- Mayor límite de descargas
- Convierte archivos
- Más resultados de búsqueda
- Otros beneficios