3 citations · 3 across the 4 of their papers we have counts for
5 papers
Delving into the pixels of adversarial samples
Blerta Lindqvist
Despite extensive research into adversarial attacks, we do not know how adversarial attacks affect image pixels. Knowing how image pixels are affected by adversarial attacks has th…
Target Training Does Adversarial Training Without Adversarial Samples
Blerta Lindqvist
Neural network classifiers are vulnerable to misclassification of adversarial samples, for which the current best defense trains classifiers with adversarial samples. However, adve…
Tricking Adversarial Attacks To Fail
Blerta Lindqvist
Recent adversarial defense approaches have failed. Untargeted gradient-based attacks cause classifiers to choose any wrong class. Our novel white-box defense tricks untargeted atta…
Minimax Defense against Gradient-based Adversarial Attacks
Blerta Lindqvist, Rauf Izmailov
State-of-the-art adversarial attacks are aimed at neural network classifiers. By default, neural networks use gradient descent to minimize their loss function. The gradient of a cl…
AutoGAN: Robust Classifier Against Adversarial Attacks
Blerta Lindqvist, Shridatt Sugrim, Rauf Izmailov
Classifiers fail to classify correctly input images that have been purposefully and imperceptibly perturbed to cause misclassification. This susceptability has been shown to be con…