• Home
  • Search
  • SecureAS: A Vulnerability Assessment System for Deep Neural Network Based on Adversarial Examples
  • Cite Icon9
  • https://doi.org/10.1109/access.2020.3001730Copy DOI Icon

SecureAS: A Vulnerability Assessment System for Deep Neural Network Based on Adversarial Examples

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep neural network (DNN) has been recently applied to many safety-critical environments. Unfortunately, recent research has proven that DNN can be vulnerable to well-designed examples, called adversarial examples. Adversarial examples can easily fool a well-performed deep learning model with little perturbations imperceptible to humans. In this paper, to tackle the DNN security issue, we propose a Model Adversarial Score (MAS) index to evaluate the vulnerability of a deep neural network, and introduce a deep learning vulnerability assessment system (SecureAS) using adversarial samples to assess the vulnerability and risk of a trained DNN in a blackbox way. We also present two adversary algorithms (FGNM and PINM) that provide better adversary images with the similar attack effect compared to existing approaches like FGSM and BIM. Our experimental results confirm the effectiveness of MAS algorithm, SecureAS, FGNM and PINM.

Loading PDF

Similar Papers
  • Research Article
  • Citations1935

Adversarial Examples: Attacks and Defenses for Deep Learning.

  • Jan 14, 2019
  • IEEE Transactions on Neural Networks and Learning Systems
  • Xiaoyong Yuan +3
  • Conference Article
  • Citations4

Defending Deep Learning Based Anomaly Detection Systems Against White-Box Adversarial Examples and Backdoor Attacks

  • Nov 12, 2020
  • Khaled Alrawashdeh +1
  • Research Article
  • Citations1

Generating traceable adversarial text examples by watermarking in the semantic space

  • Nov 26, 2022
  • Journal of Electronic Imaging
  • Mingjie Li +2
  • Research Article
  • Citations1

Generating watermarked adversarial texts

  • Mar 28, 2023
  • Journal of Electronic Imaging
  • Mingjie Li +3
  • Research Article
  • Citations2

Restoration of Adversarial Examples Using Image Arithmetic Operations

  • Jan 01, 2022
  • Intelligent Automation & Soft Computing
  • Kazim Ali +1
  • Research Article
  • Citations198

Improving the Reliability of Deep Neural Networks in NLP: A Review

  • Nov 16, 2019
  • Knowledge-Based Systems
  • Basemah Alshemali +1
  • Research Article
  • Citations8

Watermarking of Deep Recurrent Neural Network Using Adversarial Examples to Protect Intellectual Property

  • Dec 26, 2021
  • Applied Artificial Intelligence
  • Pulkit Rathi +2
  • Research Article
  • Citations603

EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

  • Apr 25, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Pin-Yu Chen +4
  • Dissertation
  • Citations29

Towards deep neural networks robust to adversarial examples

  • Feb 21, 2021
  • Alexander Matyasko
  • Research Article
  • Citations37

Fooling deep neural detection networks with adaptive object-oriented adversarial perturbation

  • Feb 20, 2021
  • Pattern Recognition
  • Yatie Xiao +2
  • Research Article
  • Citations152

Assessing the Threat of Adversarial Examples on Deep Neural Networks for Remote Sensing Scene Classification: Attacks and Defenses

  • Jun 16, 2020
  • IEEE Transactions on Geoscience and Remote Sensing
  • Yonghao Xu +2
  • Research Article
  • Citations28

Target attack on biomedical image segmentation model based on multi-scale gradients

  • Dec 17, 2020
  • Information Sciences
  • Mingwen Shao +3
  • Research Article
  • Citations32

CAGFuzz: Coverage-Guided Adversarial Generative Fuzzing Testing for Image-Based Deep Learning Systems

  • Nov 01, 2022
  • IEEE Transactions on Software Engineering
  • Pengcheng Zhang +3
  • Research Article

An Ensemble Denoiser Based on Generative Adversarial Networks to Eliminate Adversarial Perturbations

  • Oct 01, 2021
  • 電腦學刊
  • Rui Yang Rui Yang +4
  • Conference Article
  • Citations10

Fooling a Neural Network in Military Environments: Random Untargeted Adversarial Example

  • Oct 01, 2018
  • Hyun Kwon +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.