Making learners robust to adversarial perturbation at test time (ie, evasion attacks finding adversarial examples) or training time (ie, data poisoning attacks) has emerged as a …
C Xiao, C Zheng - … of the IEEE/CVF Conference on …, 2020 - openaccess.thecvf.com
Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead …
YH Wu, CH Yuan, SH Wu - International Conference on …, 2020 - proceedings.mlr.press
Deep neural networks are shown to be vulnerable to adversarial attacks. This motivates robust learning techniques, such as the adversarial training, whose goal is to learn a …
R Muthukumar, J Sulam - SIAM Journal on Mathematics of Data Science, 2023 - SIAM
This work studies the adversarial robustness of parametric functions composed of a linear predictor and a nonlinear representation map. Our analysis relies on sparse local …
E Abad Rocamora, MF Sahin, F Liu… - Advances in …, 2022 - proceedings.neurips.cc
Abstract Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently. However, robustness of PNs is unclear and thus obtaining …
We develop and study new adversarial perturbations that enable an attacker to gain control over decisions in generic Artificial Intelligence (AI) systems including deep learning neural …
S Zhu, X Zhang, D Evans - International Conference on …, 2020 - proceedings.mlr.press
Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we …
A Montanari, Y Wu - Mathematical Statistics and Learning, 2023 - ems.press
A substantial body of empirical work documents the lack of robustness in deep learning models to adversarial examples. Recent theoretical work proved that adversarial examples …
Deep learning models have been shown to be successful in accelerating MRI reconstruction, over traditional methods. However, it has been observed that these methods …