mlsanityData to 7 Oct 2026

Improving Adversarial Robustness via Phase and Amplitude-aware Prompting

arXiv 2502.03758 ↗First posted 6 Feb 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are found to be vulnerable to adversarial perturbations. The prompt-based defense has been increasingly studied due to its high efficiency. However, existing prompt-based defenses mainly exploited mixed prompt patterns, where critical patterns closely related to object semantics lack sufficient focus. The phase and amplitude spectra have been proven to be highly related to specific semantic patterns and crucial for robustness. To this end, in this paper, we propose a Phase and Amplitude-aware Prompting (PAP) defense. Specifically, we construct phase-level and amplitude-level prompts for each class, and adjust weights for prompting according to the model's robust performance under these prompts during training. During testing, we select prompts for each image using its predicted label to obtain the prompted image, which is inputted to the model to get the final prediction. Experimental results demonstrate the effectiveness of our method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 47 references that are in the map. First posted on arXiv 6 Feb 2025.

Builds on

30 of 47 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Wide Residual Networkscited by 3,057
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  11. 2022Diffusion Models for Adversarial Purificationcited by 469
  12. 2018Spatially Transformed Adversarial Examplescited by 195
18 more
  1. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  2. 2020Adversarial Self-Supervised Contrastive Learningcited by 138
  3. 2018Adversarial Reprogramming of Neural Networkscited by 115
  4. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  5. 2020Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resourcescited by 83
  6. 2023Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Modelscited by 79
  7. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
  8. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  9. 2023CFA: Class-wise Calibrated Fair Adversarial Trainingcited by 53
  10. 2022Fairness Reprogrammingcited by 33
  11. 2022Visual Prompting for Adversarial Robustnesscited by 33
  12. 2023Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approachcited by 24
  13. 2022Exploring the Relationship between Architecture and Adversarially Robust Generalizationcited by 23
  14. 2023Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Promptingcited by 12
  15. 2023Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularizationcited by 10
  16. 2021Two-Face: Adversarial Audit of Commercial Face Recognition Systemscited by 8
  17. 2021Semantic-Preserving Adversarial Text Attackscited by 5
  18. 2022Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attackscited by 4

Built on by

Not cited yet.