ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2412.11168
77
0

PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks

15 December 2024
Jin Li
Zitong Yu
Ziqiang He
Zhong Wang
Xiangui Kang
    AAML
ArXivPDFHTML
Abstract

Imperceptible adversarial attacks have recently attracted increasing research interests. Existing methods typically incorporate external modules or loss terms other than a simple lpl_plp​-norm into the attack process to achieve imperceptibility, while we argue that such additional designs may not be necessary. In this paper, we rethink the essence of imperceptible attacks and propose two simple yet effective strategies to unleash the potential of PGD, the common and classical attack, for imperceptibility from an optimization perspective. Specifically, the Dynamic Step Size is introduced to find the optimal solution with minimal attack cost towards the decision boundary of the attacked model, and the Adaptive Early Stop strategy is adopted to reduce the redundant strength of adversarial perturbations to the minimum level. The proposed PGD-Imperceptible (PGD-Imp) attack achieves state-of-the-art results in imperceptible adversarial attacks for both untargeted and targeted scenarios. When performing untargeted attacks against ResNet-50, PGD-Imp attains 100%\%% (+0.3%\%%) ASR, 0.89 (-1.76) l2l_2l2​ distance, and 52.93 (+9.2) PSNR with 57s (-371s) running time, significantly outperforming existing methods.

View on arXiv
@article{li2025_2412.11168,
  title={ PGD-Imp: Rethinking and Unleashing Potential of Classic PGD with Dual Strategies for Imperceptible Adversarial Attacks },
  author={ Jin Li and Zitong Yu and Ziqiang He and Z. Jane Wang and Xiangui Kang },
  journal={arXiv preprint arXiv:2412.11168},
  year={ 2025 }
}
Comments on this paper