Strengthening Deep Neural Networks: Making AI Less Susceptible to Adversarial Trickery by Katy Warr
English | July 3rd, 2019 | ISBN: 1492044954 | 246 pages | EPUB (True/Retail Copy) | 40.76 MB
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.