Katy Warr

Broschiertes Buch

Strengthening Deep Neural Networks

Making AI Less Susceptible to Adversarial Trickery

Beschreibung

As Deep Neural Networks (DNNs) become increasingly common in real-world applications, the potential to "fool" them presents a new attack vector. Warr examines the motivations attackers have for exploiting flaws in DNN algorithms and how to assess the threat to systems incorporating neural network technology.

Autor

Katy Warr works at Roke Manor Research in the UK creating solutions for complex real-world problems. She specializes in AI and data analytics and leads the company's technical strategy in these areas. Previously she worked at IBM UK Laboratories, architecting and developing software for a variety of distributed enterprise products with an emphasis on transactional integrity and security. Katy gained her degree in AI and Computer Science from the University of Edinburgh at a time when there was insufficient compute power and data available for deep learning to be much more than a theoretical pursuit. Fast forward a few years and she considers herself fortunate to witness this exciting field becoming mainstream.

Produktdetails

• Verlag: O'Reilly Media
• Seitenzahl: 244
• Erscheinungstermin: 3. September 2019
• Englisch
• Abmessung: 233mm x 177mm x 15mm
• Gewicht: 406g
• ISBN-13: 9781492044956
• ISBN-10: 1492044954
• Artikelnr.: 55171234