Search Results for author:
Found 2 papers, 1 papers with code
Resilience of Entropy Model in Distributed Neural Networks
As such, in this paper we formulate and investigate the resilience of entropy models to intentional interference (e. g., adversarial attacks) and unintentional interference (e. g., weather changes and motion blur).
Adversarial Machine Learning in Latent Representations of Neural Networks
Our experimental results support our theoretical findings by showing that the compressed latent representations can reduce the success rate of adversarial attacks by 88% in the best case and by 57% on the average compared to attacks to the input space.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
