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

While adversarial training has been extensively studied for ResNet architectures and low
resolution datasets like CIFAR-10, much less is known for ImageNet. Given the recent …

The robust generalization of models to rare in-distribution (ID) samples drawn from the long
tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the …

The machine learning community has witnessed a drastic change in the training pipeline
pivoted by those" foundation models" with unprecedented scales. However the field of …

The current study investigates the robustness of deep learning models for accurate medical
diagnosis systems with a specific focus on their ability to maintain performance in the …

In this paper, we explore the transformative potential of deep learning in dental radiology,
focusing on its applications in disease detection, image segmentation, and treatment …

With the prevalence of the Pretraining-Finetuning paradigm in transfer learning the
robustness of downstream tasks has become a critical concern. In this work we delve into …

We conduct experiments on the impact of increasing inference-time compute in reasoning
models (specifically OpenAI o1-preview and o1-mini) on their robustness to adversarial …

We propose Instruct2Attack (I2A), a language-guided semantic attack that generates
semantically meaningful perturbations according to free-form language instructions. We …

While prior research has proposed a plethora of methods that build neural classifiers robust
against adversarial robustness, practitioners are still reluctant to adopt them due to their …