Similarity metrics have played a significant role in computer vision to capture the underlying
semantics of images. In recent years, advanced similarity metrics, such as the Learned …

The robustness of image segmentation has been an important research topic in the past few
years as segmentation models have reached production-level accuracy. However, like …

In medical imaging, segmentation models have known a significant improvement in the past
decade and are now used daily in clinical practice. However, similar to classification models …

We propose a new defense mechanism against adversarial at-tacks inspired by an optical
co-processor, providing robustness without compromising natural accuracy in both white …

Adversarial attacks have been a looming and unaddressed threat in the industry. However,
through a decade-long history of the robustness evaluation literature, we have learned that …

Robustness to adversarial attacks is typically obtained through expensive adversarial
training with Projected Gradient Descent. Here we introduce ROPUST, a remarkably simple …

Recent advances in adversarial machine learning have shown that defenses considered to
be robust are actually susceptible to adversarial attacks which are specifically customized to …

Randomized smoothing is the dominant standard for provable defenses against adversarial
examples. Nevertheless, this method has recently been proven to suffer from important …

In recent years, there has been a remarkable surge in advancements at the crossroads of
deep learning and medicine, particularly in the realm of medical imaging. This rapid …

Traditionally, adversarial examples have been defined as imperceptible perturbations that
fool deep neural networks. This thesis challenges this view by examining unrestricted …