ROBUSTNESS OF DEEP NEURAL NETWORKS IN ADVERSARIAL EXAMPLES

被引：0

作者：

Teng, Da ^{[1
]}

Song, Xiao m ^{[1
]}

Gong, Guanghong ^{[1
]}

Han, Liang ^{[1
]}

机构：

[1] Beihang Univ, Sch Automat, Beijing, Peoples R China

来源：

INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING-THEORY APPLICATIONS AND PRACTICE | 2017年 / 24卷 / 02期

关键词：

machine learning; deep learning; neural networks; adversarial examples; COMMAND;

D O I：

暂无

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Deep neural networks have achieved state-of-the-art performance in many artificial intelligence areas, such as object recognition, speech recognition, and machine translation. While deep neural networks have high expression capabilities, they are prone to over fitting due to the high dimensionalities of the networks. In recent applications, deep neural networks have been found to be unstable in adversarial perturbations, which are small but can increase the network's prediction errors. This paper proposes a novel training algorithm to improve the robustness of the neural networks in adversarial examples.

引用

页码：123 / 133

页数：11

共 50 条

[21] Improving Adversarial Robustness of Deep Neural Networks via Linear Programming
Tang, Xiaochao
Yang, Zhengfeng
Fu, Xuanming
Wang, Jianlin
Zeng, Zhenbing
THEORETICAL ASPECTS OF SOFTWARE ENGINEERING, TASE 2022, 2022, 13299 : 326 - 343
[22] CSTAR: Towards Compact and Structured Deep Neural Networks with Adversarial Robustness
Phan, Huy
Yin, Miao
Sui, Yang
Yuan, Bo
Zonouz, Saman
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 2, 2023, : 2065 - 2073
[23] Interpreting and Improving Adversarial Robustness of Deep Neural Networks With Neuron Sensitivity
Zhang, Chongzhi
Liu, Aishan
Liu, Xianglong
Xu, Yitao
Yu, Hang
Ma, Yuqing
Li, Tianlin
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2021, 30 : 1291 - 1304
[24] MRobust: A Method for Robustness against Adversarial Attacks on Deep Neural Networks
Liu, Yi-Ling
Lomuscio, Alessio
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[25] Exploring the Impact of Conceptual Bottlenecks on Adversarial Robustness of Deep Neural Networks
Rasheed, Bader
Abdelhamid, Mohamed
Khan, Adil
Menezes, Igor
Khatak, Asad Masood
IEEE ACCESS, 2024, 12 : 131323 - 131335
[26] DLR: Adversarial examples detection and label recovery for deep neural networks
Han, Keji
Ge, Yao
Wang, Ruchuan
Li, Yun
PATTERN RECOGNITION LETTERS, 2025, 188 : 133 - 139
[27] Detection of Adversarial Examples in Deep Neural Networks with Natural Scene Statistics
Kherchouche, Anouar
Fezza, Sid Ahmed
Hamidouche, Wassim
Deforge, Olivier
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[28] Neuron Selecting: Defending Against Adversarial Examples in Deep Neural Networks
Zhang, Ming
Li, Hu
Kuang, Xiaohui
Pang, Ling
Wu, Zhendong
INFORMATION AND COMMUNICATIONS SECURITY (ICICS 2019), 2020, 11999 : 613 - 629
[29] Creating Simple Adversarial Examples for Speech Recognition Deep Neural Networks
Redden, Nathaniel
Bernard, Ben
Straub, Jeremy
2019 IEEE 16TH INTERNATIONAL CONFERENCE ON MOBILE AD HOC AND SENSOR SYSTEMS WORKSHOPS (MASSW 2019), 2019, : 58 - 62
[30] Detecting adversarial examples via prediction difference for deep neural networks
Guo, Feng
Zhao, Qingjie
Li, Xuan
Kuang, Xiaohui
Zhang, Jianwei
Han, Yahong
Tan, Yu-an
INFORMATION SCIENCES, 2019, 501 : 182 - 192

← 1 2 3 4 5 →