Analyzing the noise robustness of deep neural networks
Deep neural networks (DNNs) are vulnerable to maliciously generated adversarial
examples. These examples are intentionally designed by making imperceptible …
examples. These examples are intentionally designed by making imperceptible …
An adversarial perturbation approach against CNN-based soft biometrics detection
The use of biometric-based authentication systems spread over daily life consumer
electronics. Over the years, researchers' interest shifted from hard (such as fingerprints …
electronics. Over the years, researchers' interest shifted from hard (such as fingerprints …
Simultaneous adversarial training-learn from others' mistakes
Z Liao - 2019 14th IEEE International Conference on Automatic …, 2019 - ieeexplore.ieee.org
Adversarial examples are maliciously tweaked images that can easily fool machine learning
techniques, such as neural networks, but they are normally not visually distinguishable for …
techniques, such as neural networks, but they are normally not visually distinguishable for …
Mixing between the Cross Entropy and the Expectation Loss Terms
The cross entropy loss is widely used due to its effectiveness and solid theoretical
grounding. However, as training progresses, the loss tends to focus on hard to classify …
grounding. However, as training progresses, the loss tends to focus on hard to classify …
TEAM: An Taylor Expansion-Based Method for Generating Adversarial Examples
Y Qian, XM Zhang, W Swaileh, L Wei, B Wang… - arXiv preprint arXiv …, 2020 - arxiv.org
Although Deep Neural Networks (DNNs) have achieved successful applications in many
fields, they are vulnerable to adversarial examples. Adversarial training is one of the most …
fields, they are vulnerable to adversarial examples. Adversarial training is one of the most …