Machine Learning models increasingly face data integrity challenges due to the use of large-
scale training datasets drawn from the Internet. We study what model developers can do if …

Adversarial training (AT) defends deep neural networks against adversarial attacks. One
challenge that limits its practical application is the performance degradation on clean …

Deep learning models have a propensity for fitting the entire training set even with random
labels, which requires memorization of every training sample. In this paper, we explore the …

Adversarial examples are inputs to machine learning models that an attacker has
intentionally designed to confuse the model into making a mistake. Such examples pose a …

Machine Learning models face increased concerns regarding the storage of personal user
data and adverse impacts of corrupted data like backdoors or systematic bias. Machine …

As machine learning algorithms are deployed on sensitive data in critical decision making
processes, it is becoming increasingly important that they are also private and fair. In this …

We perform a study on the generalization ability of the wide two-layer ReLU neural network
on $\mathbb {R} $. We first establish some spectral properties of the neural tangent kernel …

It is well known that machine learning methods can be vulnerable to adversarially-chosen
perturbations of their inputs. Despite significant progress in the area, foundational open …

Abstract The real-world Facial Expression Recognition (FER) datasets usually exhibit
complex scenarios with coupled noise annotations and imbalanced classes distribution …

Benign overfitting is the phenomenon wherein none of the predictors in the hypothesis class
can achieve perfect accuracy (ie, non-realizable or noisy setting), but a model that …