In the past few years, it has become increasingly evident that deep neural networks are not
resilient enough to withstand adversarial perturbations in input data, leaving them …

Abstract Deep Convolutional Neural Networks (CNNs) have long been the architecture of
choice for computer vision tasks. Recently, Transformer-based architectures like Vision …

Recent advances in attention-based networks have shown that Vision Transformers can
achieve state-of-the-art or near state-of-the-art results on many image classification tasks …

Following the success in advancing natural language processing and understanding,
transformers are expected to bring revolutionary changes to computer vision. This work …

Leave-One-Out (LOO) scores provide estimates of feature importance in neural networks, for
adversarial attacks. In this work, we present context-free word scores as a query-efficient …

Transformers are emerging as the new workhorse of NLP, showing great success across
tasks. Unlike LSTMs, transformers process input sequences entirely through self-attention …

Generalization and robustness are both key desiderata for designing machine learning
methods. Adversarial training can enhance robustness, but past work often finds it hurts …

Deep learning models are often evaluated in scenarios where the data distribution is
different from those used in the training and validation phases. The discrepancy presents a …

Pre-trained programming language (PL) models (such as CodeT5, CodeBERT,
GraphCodeBERT, etc.,) have the potential to automate software engineering tasks involving …

Convolutional Neural Networks (CNNs) have become the de facto gold standard in
computer vision applications in the past years. Recently, however, new model architectures …