Many state-of-the-art ML models have outperformed humans in various tasks such as image
classification. With such outstanding performance, ML models are widely used today …

Machine learning techniques in medical imaging systems are accurate, but minor
perturbations in the data known as adversarial attacks can fool them. These attacks make …

Adversarial attacks in medical AI imaging systems can lead to misdiagnosis and insurance
fraud as recently highlighted by Finlayson et. al. in Science 2019. They can also be carried …

Today, Artificial Intelligence (AI) and Machine Learning/Deep Learning (ML/DL) have
become the hottest areas in information technology. In our society, many intelligent devices …

As machine learning (ML) systems have been dramatically integrated into a broad range of
decision-making-sensitive applications for the past years, adversarial attacks and data …

In this work we ask the question: is an ensemble of single hidden layer sign activation 01
loss networks more robust to white box and black box adversarial attacks than an ensemble …

Abstract Machine translation software, image captioning, grammar check (Grammarly),
chatbot, real-time captioning and translation, music genre classification, and document …

Recent work has shown the defense of 01 loss sign activation neural networks against
image classification adversarial attacks. A public challenge to attack the models on CIFAR10 …

TOWARDS ADVERSARIAL ROBUSTNESS WITH 01 LOSS MODELS, AND NOVEL
CONVOLUTIONAL NEURAL NET SYSTEMS FOR ULTRASOUND IMAGES by Page 1 …

The zero-one loss function is less sensitive to outliers than convex surrogate losses such as
hinge and cross-entropy. However, as a non-convex function, it has a large number of local …