首页> 外文OA文献 >On Robustness of Deep Neural Networks: A Comprehensive Study on the Effect of Architecture and Weight Initialization to Susceptibility and Transferability of Adversarial Attacks

【2h】

On Robustness of Deep Neural Networks: A Comprehensive Study on the Effect of Architecture and Weight Initialization to Susceptibility and Transferability of Adversarial Attacks

机译：深度神经网络的鲁棒性：综合建筑与体重初始化对对抗敏感性和可转移性的综合研究

代理获取

本网站仅为用户提供外文OA文献查询和代理获取服务，本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文，但由于OA文献来源多样且变更频繁，仍可能出现获取不到、文献不完整或与标题不符等情况，如果获取不到我们将提供退款服务。请知悉。

页面导航

著录项
引文网络
相似文献
相关主题

著录项

作者
Ibrahim Ben Daya; Mohammad Javad Shaifee; Michelle Karg; Christian Scharfenderger; Alexander Wong;
展开▼
作者单位

展开▼
年度 2018
总页数
原文格式 PDF
正文语种
中图分类

相似文献

外文文献
中文文献
专利

1. Adversarial Learning Targeting Deep Neural Network Classification: A Comprehensive Review of Defenses Against Attacks [J] . Proceedings of the IEEE . 2020,第3期

机译：针对深度神经网络分类的对抗学习：针对攻击的防御方法的全面综述
2. TOWARDS AN OPTIMAL SET OF INITIAL WEIGHTS FOR A DEEP NEURAL NETWORK ARCHITECTURE [J] . Saadi A., Belhadef H. Neural Network World . 2019,第6期

机译：深层神经网络架构的最佳初始权重集
3. Flexible Bayesian Inference by Weight Transfer for Robust Deep Neural Networks [J] . Thi Thu Thao KHONG, Takashi NAKADA, Yasuhiko NAKASHIMA IEICE transactions on information and systems . 2021,第11期

机译：灵活的贝叶斯推断，重量转移为强大的深神经网络
4. MRobust: A Method for Robustness against Adversarial Attacks on Deep Neural Networks [C] . Yi-Ling Liu, Alessio Lomuscio International Joint Conference on Neural Networks . 2020

机译：MRobust：一种针对深度神经网络的对抗攻击的鲁棒性方法
5. Adversarial Attacks Against Deep Neural Networks [D] . Koirala, Nirajan. 2021

机译：对深神经网络的对抗攻击
6. Universal adversarial attacks on deep neural networks for medical image classification [O] . Hokuto Hirano, Akinori Minagi, Kazuhiro Takemoto 2021

机译：对医学图像分类深神经网络的普遍对抗攻击
7. Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack [O] . Zhezhi He, Adnan Siraj Rakin, Deliang Fan 2019

机译：参数噪声注射：可训练随机性，以提高对抗对抗攻击的深度神经网络鲁棒性

On Robustness of Deep Neural Networks: A Comprehensive Study on the Effect of Architecture and Weight Initialization to Susceptibility and Transferability of Adversarial Attacks

著录项

引文网络

相似文献

相关主题

期刊订阅