Although current deep learning techniques have yielded superior performance on various
computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial …

Abstract Large pre-trained Vision-Language Models (VLMs) like CLIP despite having
remarkable generalization ability are highly vulnerable to adversarial examples. This work …

Fast Adversarial Training (FAT) not only improves the model robustness but also reduces
the training cost of standard adversarial training. However, fast adversarial training often …

Deep learning has revolutionized computer vision with phenomenal success and
widespread applications. Despite impressive results in complex problems, neural networks …

We address the problem of stably and efficiently training a deep neural network robust to
adversarial perturbations bounded by an $ l_1 $ norm. We demonstrate that achieving …

Graph Neural Networks (GNNs) have achieved impressive performance in collaborative
filtering. However, recent studies show that GNNs tend to yield inferior performance when …

Adversarial training is often formulated as a min-max problem however concentrating only
on the worst adversarial examples causes alternating repetitive confusion of the model ie …

Image inpainting based on generative adversarial networks (GANs) has achieved great
success in producing visually plausible images and plays an important role in many real …

Adversarial training (AT) has become an effective defense method against adversarial
examples (AEs) and it is typically framed as a bi-level optimization problem. Among various …

While adversarial training is generally used as a defense mechanism, recent works show
that it can also act as a regularizer. By co-training a neural network on clean and adversarial …