Temporal shuffling for defending deep action recognition models against adversarial attacks

Jaehui Hwang; Huan Zhang; Jun-Ho Choi; Cho‐Jui Hsieh; Jong‐Seok Lee

doi:10.1016/j.neunet.2023.10.033

ScienceGate Book Chapters

JOURNAL ARTICLE

Temporal shuffling for defending deep action recognition models against adversarial attacks

Jaehui Hwang Huan Zhang Jun-Ho Choi Cho‐Jui Hsieh Jong‐Seok Lee

Year: 2023 Journal: Neural Networks Vol: 169 Pages: 388-397 Publisher: Elsevier BV

DOI: 10.1016/j.neunet.2023.10.033

Get Full-Text PDF Get Analytical Report

Keywords:

Computer science Shuffling Adversarial system Artificial intelligence Action recognition Robustness (evolution) Convolutional neural network Action (physics) Generalization Machine learning Pattern recognition (psychology) Class (philosophy) Mathematics

Metrics

Cited By

1.02

FWCI (Field Weighted Citation Impact)

Refs

0.77

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Adversarial Robustness in Machine Learning

Physical Sciences → Computer Science → Artificial Intelligence

Anomaly Detection Techniques and Applications

Physical Sciences → Computer Science → Artificial Intelligence

Human Pose and Action Recognition

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Temporal shuffling for defending deep action recognition models against adversarial attacks

Metrics

Citation History

Topics

Related Documents

Defending Deep Learning Models Against Adversarial Attacks

Defending AI-Based Automatic Modulation Recognition Models Against Adversarial Attacks

Defending against adversarial attacks in deep neural networks

DiffDefense: Defending Against Adversarial Attacks via Diffusion Models

Defending AI Models Against Adversarial Attacks in Smart Grids Using Deep Learning