Characterizing Adversarial Samples of Convolutional Neural Networks

被引：0

作者：

Jiang, Cheng ^{[1
]}

Zhao, Qiyang ^{[1
]}

Liu, Yuzhong ^{[2
]}

机构：

[1] Beihang Univ, NLSDE, Beijing, Peoples R China

[2] Tech Infrastruct Grp JD, Beijing, Peoples R China

来源：

2018 11TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2018) | 2018年

关键词：

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

Adversarial samples aim to make deep convolutional neural networks predict incorrectly under small perturbations. This paper investigates non-targeted adversarial samples of convolutional neural networks and makes a primitive attempt to characterize adversarial samples. Two observations are made: first, adversarial perturbations are mainly in the high-frequency domain; second, adversarial categories usually have strong semantic relevance to the original categories. Our two observations provide a solid basis to understand the behavior of convolutional neural networks and thus to improve their robustness against adversarial samples.

引用

页数：6

共 50 条

[21] Convolutional Neural Networks for Vehicle Re-identification with Adversarial Loss
Shang, Linzhi
Liu, Lizhen
Song, Wei
Zhao, Xinlei
Du, Chao
PROCEEDINGS OF 2019 IEEE 9TH INTERNATIONAL CONFERENCE ON ELECTRONICS INFORMATION AND EMERGENCY COMMUNICATION (ICEIEC 2019), 2019, : 117 - 121
[22] Grasping Adversarial Attacks on Deep Convolutional Neural Networks for Cholangiocarcinoma Classification
Diyasa, I. Gede Susrama Mas
Wahid, Radical Rakhman
Amiruddin, Brilian Putra
2021 INTERNATIONAL CONFERENCE ON E-HEALTH AND BIOENGINEERING (EHB 2021), 9TH EDITION, 2021,
[23] Visual Analytics of Neuron Vulnerability to Adversarial Attacks on Convolutional Neural Networks
Li, Yiran
Wang, Junpeng
Fujiwara, Takanori
Ma, Kwan-Liu
ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS, 2023, 13 (04)
[24] Understanding and improving adversarial transferability of vision transformers and convolutional neural networks
Chen, Zhiyu
Xu, Chi
Lv, Huanhuan
Liu, Shangdong
Ji, Yimu
INFORMATION SCIENCES, 2023, 648
[25] Retrieval-Augmented Convolutional Neural Networks against Adversarial Examples
Zhao , Jake
Cho, Kyunghyun
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 11555 - 11563
[26] Impact of White-Box Adversarial Attacks on Convolutional Neural Networks
Podder, Rakesh
Ghosh, Sudipto
2024 International Conference on Emerging Trends in Networks and Computer Communications, ETNCC 2024 - Proceedings, 2024, : 41 - 49
[27] Effectiveness of Adversarial Attacks on Class-Imbalanced Convolutional Neural Networks
Possas, Rafael
Zhou, Ying
NEURAL INFORMATION PROCESSING (ICONIP 2017), PT II, 2017, 10635 : 333 - 342
[28] Error Resiliency and Adversarial Robustness in Convolutional Neural Networks: An Empirical Analysis
Barbareschi, Mario
Barone, Salvatore
Casola, Valentina
Della Torca, Salvatore
INTERNET OF THINGS, IFIPIOT 2024, 2025, 737 : 149 - 160
[29] On the limitations of adversarial training for robust image classification with convolutional neural networks
Carletti, Mattia
Sinigaglia, Erto
Terzi, Matteo
Susto, Gian Antonio
INFORMATION SCIENCES, 2024, 675
[30] Comparison of the Resilience of Convolutional and Cellular Neural Networks Against Adversarial Attacks
Horvath, Andras
2022 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS 22), 2022, : 2348 - 2352

← 1 2 3 4 5 →