Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …

Most prior works on physical adversarial attacks mainly focus on the attack performance but
seldom enforce any restrictions over the appearance of the generated adversarial patches …

Self-supervised learning in computer vision aims to pre-train an image encoder using a
large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can …

Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …

We investigate a new method for injecting backdoors into machine learning models, based
on compromising the loss-value computation in the model-training code. We use it to …

Though deep neural networks (DNNs) have demonstrated excellent performance in
computer vision, they are susceptible and vulnerable to carefully crafted adversarial …

Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …

Patch attacks, one of the most threatening forms of physical attack in adversarial examples,
can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous …

Advanced Driver Assistance Systems (ADAS) are advanced technologies that assist drivers
with vehicle operation and navigation. Recent improvements and brisk expansion in the …

To obtain, deterministic guarantees of adversarial robustness, specialized training methods
are used. We propose, SABR, a novel such certified training method, based on the key …