Deep learning has presented remarkable progress in various tasks. Despite the excellent
performance, deep learning models remain not robust, especially to well-designed …

In this paper we propose a novel human-centered approach for detecting forgery in face
images, using dynamic prototypes as a form of visual explanations. Currently, most state-of …

Deep learning has gained tremendous success and great popularity in the past few years.
However, deep learning systems are suffering several inherent weaknesses, which can …

The rapid growth of deep learning applications in real life is accompanied by severe safety
concerns. To mitigate this uneasy phenomenon, much research has been done providing …

We propose a spurious region guided refinement approach for robustness verification of
deep neural networks. Our method starts with applying the DeepPoly abstract domain to …

Recently, many applications have begun to employ deep neural networks (DNN), such as
image recognition and safety-critical applications, for more accurate results. One of the most …

Despite regularizing the Jacobians of neural networks to enhance model robustness has
directly theoretical correlation with model prediction stability, a large defense performance …

Quantifying the robustness of neural networks or verifying their safety properties against
input uncertainties or adversarial attacks have become an important research area in …

Adversarial Robustness for Machine Learning summarizes the recent progress on this topic
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …

In safety-critical machine learning applications, it is crucial to defend models against
adversarial attacks---small modifications of the input that change the predictions. Besides …