mlsanityData to 7 Oct 2026

Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generation

arXiv 2405.05075 ↗First posted 8 May 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

This work studies sparse adversarial perturbations, including both unstructured and structured ones. We propose a framework based on a white-box PGD-like attack method named Sparse-PGD to effectively and efficiently generate such perturbations. Furthermore, we combine Sparse-PGD with a black-box attack to comprehensively and more reliably evaluate the models' robustness against unstructured and structured sparse adversarial perturbations. Moreover, the efficiency of Sparse-PGD enables us to conduct adversarial training to build robust models against various sparse perturbations. Extensive experiments demonstrate that our proposed attack algorithm exhibits strong performance in different scenarios. More importantly, compared with other robust models, our adversarially trained model demonstrates state-of-the-art robustness against various sparse attacks. Codes are available at https://github.com/CityU-MLO/sPGD.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 60 of its 79 references that are in the map. First posted on arXiv 8 May 2024.

Builds on

60 of 79 references.

References · 60

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  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. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  9. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  10. 2016Adversarial examples in the physical worldcited by 1,762
  11. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  12. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
38 more
  1. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  2. 2016Adversarial Machine Learning at Scalecited by 934
  3. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  4. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  5. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  6. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  7. 2019Adversarial Training for Free!cited by 638
  8. 2017One pixel attack for fooling deep neural networkscited by 579
  9. 2017Adversarial Patchcited by 514
  10. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  11. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  12. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  13. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  14. 2019Simple Black-box Adversarial Attackscited by 249
  15. 2019What's Hidden in a Randomly Weighted Neural Network?cited by 236
  16. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  17. 2021Improving Robustness using Generated Datacited by 233
  18. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  19. 2020Understanding and Improving Fast Adversarial Trainingcited by 213
  20. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  21. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  22. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
  23. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  24. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  25. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  26. 2021Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?cited by 113
  27. 2018LaVAN: Localized and Visible Adversarial Noisecited by 112
  28. 2019Sparse and Imperceivable Adversarial Attackscited by 95
  29. 2018SparseFool: a few pixels make a big differencecited by 94
  30. 2018GenAttack: Practical Black-box Attacks with Gradient-Free Optimizationcited by 82
  31. 2020Understanding Catastrophic Overfitting in Single-step Adversarial Trainingcited by 75
  32. 2020PatchAttack: A Black-box Texture-based Attack with Reinforcement Learningcited by 67
  33. 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
  34. 2023Decoupled Kullback-Leibler Divergence Losscited by 58
  35. 2020Adversarial Training against Location-Optimized Adversarial Patchescited by 50
  36. 2021Mind the box: l1-APGD for sparse adversarial attacks on image classifierscited by 50
  37. 2019Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimizationcited by 49
  38. 2022Make Some Noise: Reliable and Efficient Single-Step Adversarial Trainingcited by 42

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMscited by 0
  2. 2026Unveiling the Backdoor Mechanism Hidden Behind Catastrophic Overfitting in Fast Adversarial Trainingcited by 0
  3. 2026USAD: Uncertainty-aware Statistical Adversarial Detectioncited by 0
  4. 2026Fast LapSum: Exact Differentiable Top-k at Million Scalecited by 0