Results (1)
Search Parameters:
Author/Affiliation: Jürgen GroßmannOpen AccessArticle
17 Pages, 1,660 KB 
On Adversarial Robustness of Quantized Neural Networks Against Direct Attacks
Abstract:
Deep Neural Networks (DNNs) prove to be susceptible to synthetically generated samples, so-called adversarial examples. Such adversarial examples aim at generating misclassifications by specifically optimizing input data for a matching perturbation. With the increasing use of deep learning on embedded devices and the resulting use of quantization techniques to compress deep neural networks, it is…
Read More(This article belongs to the SP17 (Special Issue on Innovation in Computing, Engineering Science & Technology 2024-25) & Section Artificial Intelligence in Computer Science (CAI))