• Home
  • Search
  • Assessing Optimizer Impact on DNN Model Sensitivity to Adversarial Examples
  • Cite Icon67
  • https://doi.org/10.1109/access.2019.2948658Copy DOI Icon

Assessing Optimizer Impact on DNN Model Sensitivity to Adversarial Examples

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

Deep Neural Networks (DNNs) have been gaining state-of-the-art achievement compared with many traditional Machine Learning (ML) models in diverse fields. However, adversarial examples challenge the further deployment and application of DNNs. Analysis has been carried out for studying the reasons of DNNs' vulnerability to adversarial perturbation and focused on model architecture. No research has been done on investigating the impact of optimization algorithms (namely, optimizers in DNNs) employed in training DNN models on models' sensitivity to adversarial examples. This paper aims to study this impact from an experimental perspective. We analyze the sensitivity of a model not only from the aspect of white-box and black-box attack setups, but also from the aspect of different types of datasets. Four common optimizers, SGD, RMSprop, Adadelta, and Adam, are investigated on structured and unstructured datasets. Extensive experiment results indicate that an optimization algorithm does pose effects on the DNN model sensitivity to adversarial examples. That is, when training models and generating adversarial examples, Adam optimizer can generate better quality adversarial examples for structured datasets, and Adadelta optimizer can generate better quality adversarial examples for unstructured datasets. In addition, the choice of optimizers does not affect the transferability of adversarial examples.

Loading PDF

Similar Papers
  • Research Article
  • Citations1

Generating watermarked adversarial texts

  • Mar 28, 2023
  • Journal of Electronic Imaging
  • Mingjie Li +3
  • Book Chapter
  • Citations30

Evaluating Defensive Distillation for Defending Text Processing Neural Networks Against Adversarial Examples

  • Jan 01, 2019
  • Marcus Soll +3
  • Research Article

Transfer-based Adversarial Attack with Rectified Adam and Color Invariance

  • Jan 01, 2022
  • International Journal of Software and Informatics
  • Jia Ding +1
  • Research Article
  • Citations23

IWA: Integrated gradient‐based white‐box attacks for fooling deep neural networks

  • Oct 28, 2021
  • International Journal of Intelligent Systems
  • Yixiang Wang +4
  • Research Article
  • Citations16

Boosting the transferability of adversarial examples via stochastic serial attack

  • Mar 07, 2022
  • Neural Networks
  • Lingguang Hao +3
  • Research Article
  • Citations6

Foolmix: Strengthen the Transferability of Adversarial Examples by Dual-Blending and Direction Update Strategy

  • Jan 01, 2024
  • IEEE Transactions on Information Forensics and Security
  • Zhankai Li +4
  • Research Article
  • Citations33

Adversarial example generation with adabelief optimizer and crop invariance

  • May 07, 2022
  • Applied Intelligence
  • Bo Yang +5
  • 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
  • Citations4

A Comprehensive Understanding of the Impact of Data Augmentation on the Transferability of 3D Adversarial Examples

  • Feb 14, 2025
  • ACM Transactions on Knowledge Discovery from Data
  • Fulan Qian +6
  • Conference Article

Enhancing the transferability of adversarial black-box attacks

  • Feb 18, 2022
  • Yuxiao Gao
  • Book Chapter
  • Citations30

Yet Another Intermediate-Level Attack

  • Jan 01, 2020
  • Qizhang Li +2
  • 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
  • Conference Article
  • Citations16

Strengthening the Transferability of Adversarial Examples Using Advanced Looking Ahead and Self-CutMix

  • Jun 01, 2022
  • Donggon Jang +2
  • Research Article
  • Citations8

ACT-Detector: Adaptive channel transformation-based light-weighted detector for adversarial attacks

  • Feb 16, 2021
  • Information Sciences
  • Jinyin Chen +4
  • Research Article
  • Citations10

AdvEWM: Generating image adversarial examples by embedding digital watermarks

  • Dec 06, 2023
  • Journal of Information Security and Applications
  • Yuexin Xiang +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.