It has been recognized that the data generated by the denoising diffusion probabilistic
model (DDPM) improves adversarial training. After two years of rapid development in …

Machine learning (ML) systems are rapidly increasing in size, are acquiring new
capabilities, and are increasingly deployed in high-stakes settings. As with other powerful …

Adversarial training suffers from the issue of robust overfitting, which seriously impairs its
generalization performance. Data augmentation, which is effective at preventing overfitting …

Adversarial training is widely used to improve the robustness of deep neural networks to
adversarial attack. However, adversarial training is prone to overfitting, and the cause is far …

Delusive attacks aim to substantially deteriorate the test accuracy of the learning model by
slightly perturbing the features of correctly labeled training examples. By formalizing this …

This chapter explores the foundational concept of robustness in Machine Learning (ML) and
its integral role in establishing trustworthiness in Artificial Intelligence (AI) systems. The …

Recent studies demonstrate that deep networks, even robustified by the state-of-the-art
adversarial training (AT), still suffer from large robust generalization gaps, in addition to the …

Synthetic aperture radar (SAR) can perform observations at all times and has been widely
used in the military field. Deep neural network (DNN)-based SAR target recognition models …

Recent studies have shown the vulnerability of CNNs under perturbation noises, which is
partially caused by the reason that the well-trained CNNs are too biased toward the object …

With the rise of Machine Learning as a Service (MLaaS) platforms, safeguarding the
intellectual property of deep learning models is becoming paramount. Among various …