Adversarial training (AT) is always formulated as a minimax problem, of which the
performance depends on the inner optimization that involves the generation of adversarial …

Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …

We propose a minimax formulation for removing backdoors from a given poisoned model
based on a small set of clean data. This formulation encompasses much of prior work on …

Current methods for training robust networks lead to a drop in test accuracy, which has led
prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning …

Recent studies have demonstrated that existing deep neural networks (DNNs) on 3D point
clouds are vulnerable to adversarial examples, especially under the white-box settings …

Deep neural networks have achieved remarkable success in machine learning, computer
vision, and pattern recognition in the last few decades. Recent studies, however, show that …

A hard challenge in developing practical face recognition (FR) attacks is due to the black-
box nature of the target FR model, ie, inaccessible gradient and parameter information to …

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial
training (SAT). However, initial FAT encounters catastrophic overfitting, ie, the robust …

This work studies the sparse adversarial attack, which aims to generate adversarial
perturbations onto partial positions of one benign image, such that the perturbed image is …

In adversarial machine learning, deep neural networks can fit the adversarial examples on
the training dataset but have poor generalization ability on the test set. This phenomenon is …