It is widely recognized that deep learning models lack robustness to adversarial examples.
An intriguing property of adversarial examples is that they can transfer across different …

We present CLAMP-ViT, a data-free post-training quantization method for vision
transformers (ViTs). We identify the limitations of recent techniques, notably their inability to …

Adversarial Training (AT), which adversarially perturb the input samples during training, has
been acknowledged as one of the most effective defenses against adversarial attacks, yet …

Damage identification in post-earthquake reinforced concrete (RC) structures based on
semantic segmentation has been recognized as a promising approach for rapid and non …

Network slicing-based communication systems can dynamically and efficiently allocate
resources for diversified services. However, due to the limitation of the network interface on …

We consider and discuss the ways in which search landscapes might contribute to the future
of explainable artificial intelligence (XAI), and vice versa. Landscapes are typically used to …

Dataset condensation, a concept within data-centric learning, efficiently transfers critical
attributes from an original dataset to a synthetic version, maintaining both diversity and …

Adversarial attacks, which manipulate input data to undermine model availability and
integrity, pose significant security threats during machine learning inference. With the advent …

Deep neural networks are vulnerable to adversarial examples, posing a threat to the models'
applications and raising security concerns. An intriguing property of adversarial examples is …

A substantial amount of variability in ECG manifested due to patient characteristics hinders
the adoption of automated analysis algorithms in clinical practice. None of the ECG …