IEEE

Robust Physical-World Attacks on Deep Learning Visual Classification

Abstract: Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input. Given that ...
GitHub

PolarFire SoC Bare Metal Library

This folder contains the PolarFire SoC Bare Metal Library. The PolarFire SoC Bare Metal Library includes: Source code for start-up code and Hardware Abstraction Layer (HAL) for the PolarFire SoC ...
IEEE

Assessing the Threat of Adversarial Examples on Deep Neural Networks for Remote Sensing Scene Classification: Attacks and Defenses

Abstract: Deep neural networks, which can learn the representative and discriminative features from data in a hierarchical manner, have achieved state-of-the-art performance in the remote sensing ...