Recent advances in artificial intelligence (AI) have led to its widespread industrial adoption,
with machine learning systems demonstrating superhuman performance in a significant …

High prevalence of mental illness and the need for effective mental health care, combined
with recent advances in AI, has led to an increase in explorations of how the field of machine …

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 …

Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to
adversarial examples, resulting from small-magnitude perturbations added to the input …

This paper investigates strategies that defend against adversarial-example attacks on image-
classification systems by transforming the inputs before feeding them to the system …

Though CNNs have achieved the state-of-the-art performance on various vision tasks, they
are vulnerable to adversarial examples---crafted by adding human-imperceptible …

We construct targeted audio adversarial examples on automatic speech recognition. Given
any audio waveform, we can produce another that is over 99.9% similar, but transcribes as …

Convolutional neural networks have demonstrated high accuracy on various tasks in recent
years. However, they are extremely vulnerable to adversarial examples. For example …

With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques,
it is critical to ensure the security and robustness of the deployed algorithms. Recently, the …

Abstract Machine learning models are often susceptible to adversarial perturbations of their
inputs. Even small perturbations can cause state-of-the-art classifiers with high" standard" …