• Home
  • Search
  • ALA: Naturalness-aware Adversarial Lightness Attack
  • Cite Icon14
  • https://doi.org/10.1145/3581783.3611914Copy DOI Icon

ALA: Naturalness-aware Adversarial Lightness Attack

  • Oct 26, 2023
  • Yihao Huang +7 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Most researchers have tried to enhance the robustness of deep neural networks (DNNs) by revealing and repairing the vulnerability of DNNs with specialized adversarial examples. Parts of the attack examples have imperceptible perturbations restricted by Lp norm. However, due to their high-frequency property, the adversarial examples can be defended by denoising methods and are hard to realize in the physical world. To avoid the defects, some works have proposed unrestricted attacks to gain better robustness and practicality. It is disappointing that these examples usually look unnatural and can alert the guards. In this paper, we propose Adversarial Lightness Attack (ALA), a white-box unrestricted adversarial attack that focuses on modifying the lightness of the images. The shape and color of the samples, which are crucial to human perception, are barely influenced. To obtain adversarial examples with a high attack success rate, we propose unconstrained enhancement in terms of the light and shade relationship in images. To enhance the naturalness of images, we craft the naturalness-aware regularization according to the range and distribution of light. The effectiveness of ALA is verified on two popular datasets for different tasks (i.e., ImageNet for image classification and Places-365 for scene recognition).

Similar Papers
  • Research Article

Adversarial Example Generation Method Based on Wavelet Transform

  • Feb 10, 2026
  • Information
  • Meng Bi +5
  • Conference Article

Dynamic Decision Boundaries for Improved Robustness against Adversarial Attacks

  • Feb 24, 2023
  • Zeyu Long
  • Research Article
  • Citations215

Seq2Sick: Evaluating the Robustness of Sequence-to-Sequence Models with Adversarial Examples

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Minhao Cheng +4
  • Research Article
  • Citations134

Self-Attention Context Network: Addressing the Threat of Adversarial Attacks for Hyperspectral Image Classification.

  • Jan 01, 2021
  • IEEE Transactions on Image Processing
  • Yonghao Xu +2
  • Conference Article
  • Citations3

Defending Against Adversarial Examples via Soft Decision Trees Embedding

  • Oct 15, 2019
  • Yingying Hua +4
  • Conference Article

Evaluation of Adversarial Attacks Based on DL in Communication Networks

  • Nov 01, 2020
  • Zhida Bao +1
  • Research Article
  • Citations3

Adversarial attack method against image classification based on haze perturbation

  • Feb 01, 2023
  • SCIENTIA SINICA Informationis
  • 伟 冯 +3
  • Conference Article
  • Citations6

Accelerating Spectral Normalization for Enhancing Robustness of Deep Neural Networks

  • Jul 01, 2021
  • Zhixin Pan +1
  • Research Article
  • Citations15

Feature-filter: Detecting adversarial examples by filtering out recessive features

  • May 20, 2022
  • Applied Soft Computing
  • Hui Liu +5
  • PDF
  • Research Article
  • Citations34

Adversarial Attack for SAR Target Recognition Based on UNet-Generative Adversarial Network

  • Oct 29, 2021
  • Remote Sensing
  • Chuan Du +1
  • PDF
  • Research Article
  • Citations17

Diversity Adversarial Training against Adversarial Attack on Deep Neural Networks

  • Mar 06, 2021
  • Symmetry
  • Hyun Kwon +1
  • PDF
  • Research Article
  • Citations8

A CMA-ES-Based Adversarial Attack on Black-Box Deep Neural Networks

  • Jan 01, 2019
  • IEEE Access
  • Xiaohui Kuang +5
  • PDF
  • Research Article
  • Citations15

Detection of adversarial attacks based on differences in image entropy

  • Aug 17, 2023
  • International Journal of Information Security
  • Gwonsang Ryu +1
  • Research Article
  • Citations7

SAR-PATT: A Physical Adversarial Attack for SAR Image Automatic Target Recognition

  • Dec 25, 2024
  • Remote Sensing
  • Binyan Luo +6
  • Conference Article
  • Citations7

FuzzGAN: A Generation-Based Fuzzing Framework for Testing Deep Neural Networks

  • Dec 01, 2022
  • Ge Han +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.