GradFuzz: Fuzzing deep neural networks with gradient vector coverage for adversarial examples

Leo Hyun Park; Soochang Chung; Jaeuk Kim; Taekyoung Kwon

doi:10.1016/j.neucom.2022.12.019

ScienceGate Book Chapters

JOURNAL ARTICLE

GradFuzz: Fuzzing deep neural networks with gradient vector coverage for adversarial examples

Leo Hyun Park Soochang Chung Jaeuk Kim Taekyoung Kwon

Year: 2022 Journal: Neurocomputing Vol: 522 Pages: 165-180 Publisher: Elsevier BV

DOI: 10.1016/j.neucom.2022.12.019

Get Full-Text PDF Get Analytical Report

Keywords:

Fuzz testing Computer science MNIST database Adversarial system Deep neural networks Machine learning Crash Artificial intelligence Set (abstract data type) Range (aeronautics) Artificial neural network Software

Metrics

Cited By

1.37

FWCI (Field Weighted Citation Impact)

Refs

0.80

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

Advanced Neural Network Applications

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Anomaly Detection Techniques and Applications

Physical Sciences → Computer Science → Artificial Intelligence

GradFuzz: Fuzzing deep neural networks with gradient vector coverage for adversarial examples

Metrics

Citation History

Topics

Related Documents

Compound adversarial examples in deep neural networks

Deep2Fuzz: Coverage-Guided Reinforcement Fuzzing towards Deep Neural Networks

Adversarial Examples in Deep Neural Networks: An Overview

Towards deep neural networks robust to adversarial examples

Towards robust adversarial examples for deep neural networks