This paper theoretically explains the intuition that simple concepts are more likely to be
learned by deep neural networks (DNNs) than complex concepts. In fact, recent studies …

Knowledge distillation is normally used to compress a big network, or teacher, onto a
smaller one, the student, by training it to match its outputs. Recently, some works have …

While adversarial training and its variants have shown to be the most effective algorithms to
defend against adversarial attacks, their extremely slow training process makes it hard to …

Ensuring the trustworthiness of large language models (LLMs) is crucial. Most studies
concentrate on fully pre-trained LLMs to better understand and improve LLMs' …

Benign overfitting, where classifiers memorize noisy training data yet still achieve a good
generalization performance, has drawn great attention in the machine learning community …

Federated Learning (FL) is susceptible to poisoning attacks, wherein compromised clients
manipulate the global model by modifying local datasets or sending manipulated model …

This paper mathematically derives an analytic solution of the adversarial perturbation on a
ReLU network, and theoretically explains the difficulty of adversarial training. Specifically …

Deep learning has been able to outperform humans in terms of classification accuracy in
many tasks. However, to achieve robustness to adversarial perturbations, the best …