Group-wise inhibition based feature regularization for robust classification

H Liu, H Wu, W Xie, F Liu… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
The convolutional neural network (CNN) is vulnerable to degraded images with even very
small variations (eg corrupted and adversarial samples). One of the possible reasons is that …

Really natural adversarial examples

A Pedraza, O Deniz, G Bueno - International Journal of Machine Learning …, 2022 - Springer
Abstract The phenomenon of Adversarial Examples has become one of the most intriguing
topics associated to deep learning. The so-called adversarial attacks have the ability to fool …

: A Dataset Generator for a Systematic Evaluation of Adversarial Robustness of Deep Learning Vision Models

F Nesti, G Rossolini, G D'Amico… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Adversarial examples represent a serious threat for deep neural networks in several
application domains and a huge amount of work has been produced to investigate them and …

Robustness analysis framework for computations associated with building performance models and immersive virtual experiments

C Chokwitthaya, Y Zhu, S Mukhopadhyay - Advanced Engineering …, 2021 - Elsevier
Building performance models (BPMs) have been used to simulate and analyze building
performance during design. While extensive research efforts have made to improve the …

Carla-gear: a dataset generator for a systematic evaluation of adversarial robustness of vision models

F Nesti, G Rossolini, G D'Amico, A Biondi… - arXiv preprint arXiv …, 2022 - arxiv.org
Adversarial examples represent a serious threat for deep neural networks in several
application domains and a huge amount of work has been produced to investigate them and …

물리적환경에서의적대적패치의공격성공률분석

정현재, 이주빈, 마유승, 이승익 - Journal of KIISE, 2023 - dbpia.co.kr
적대적 패치는 물리적 환경에서의 대표적인 적대적 예제 공격으로 알려져 있다. 하지만 적대적
패치의 효과에 관한 대부분의 연구는 물리적 환경이 아닌 디지털 환경을 기반으로 공격 …