mlsanityData to 7 Oct 2026

Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attacks

arXiv 2006.12834 ↗First posted 23 Jun 2020cs.LG cs.CR cs.CVcited by 65

Not on the map. Why?

Abstract (arXiv)

We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and query efficiency for multiple sparse attack models: l0-bounded perturbations, adversarial patches, and adversarial frames. The l0-version of untargeted Sparse-RS outperforms all black-box and even all white-box attacks for different models on MNIST, CIFAR-10, and ImageNet. Moreover, our untargeted Sparse-RS achieves very high success rates even for the challenging settings of 20×20 adversarial patches and 2-pixel wide adversarial frames for 224×224 images. Finally, we show that Sparse-RS can be applied to generate targeted universal adversarial patches where it significantly outperforms the existing approaches. The code of our framework is available at https://github.com/fra31/sparse-rs.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 10; 2023: 10; 2024: 15; 2025: 12; 2026: 6.

65 papers.

Sort:

By area:

  1. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscited by 450
  2. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  3. 2021Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spacescited by 51
  4. 2023Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMscited by 26
  5. 2021Efficient Certified Defenses Against Patch Attacks on Image Classifierscited by 23
  6. 2021Adversarial Robustness against Multiple and Single lp-Threat Models via Quick Fine-Tuning of Robust Classifierscited by 23
  7. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
  8. 2022Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustnesscited by 23
  9. 2023Efficient Decision-based Black-box Patch Attacks on Video Recognitioncited by 21
  10. 2024Transferable Adversarial Attacks on SAM and Its Downstream Modelscited by 20
  11. 2021Meta Adversarial Training against Universal Patchescited by 19
  12. 2023Query-Efficient Decision-based Black-Box Patch Attackcited by 19
38 more
  1. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  2. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  3. 2022Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defensecited by 14
  4. 2021EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware Detectioncited by 13
  5. 2023Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Modelscited by 12
  6. 2021Adversarial Token Attacks on Vision Transformerscited by 11
  7. 2024Cross-Modality Attack Boosted by Gradient-Evolutionary Multiform Optimizationcited by 11
  8. 2021Transferable Sparse Adversarial Attackcited by 9
  9. 2025Towards Effective and Sparse Adversarial Attack on Spiking Neural Networks via Breaking Invisible Surrogate Gradientscited by 9
  10. 2021Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attackscited by 7
  11. 2024σ-zero: Gradient-based Optimization of ℓ0-norm Adversarial Examplescited by 7
  12. 2024BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attackcited by 7
  13. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  14. 2023LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfercited by 6
  15. 2021Robust Classification Under ℓ0 Attack for the Gaussian Mixture Modelcited by 5
  16. 2022Adversarial Scratches: Deployable Attacks to CNN Classifierscited by 5
  17. 2023Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectorscited by 5
  18. 2023GSE: Group-wise Sparse and Explainable Adversarial Attackscited by 5
  19. 2024Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metricscited by 5
  20. 2022On the interplay of adversarial robustness and architecture components: patches, convolution and attentioncited by 4
  21. 2024Sparse-PGD: A Unified Framework for Sparse Adversarial Perturbations Generationcited by 4
  22. 2022LP-BFGS attack: An adversarial attack based on the Hessian with limited pixelscited by 3
  23. 2024BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Taskscited by 3
  24. 2024Query-Efficient Video Adversarial Attack with Stylized Logo on Service Computingcited by 3
  25. 2025LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attackscited by 3
  26. 2022Level Up with ML Vulnerability Identification: Leveraging Domain Constraints in Feature Space for Robust Android Malware Detectioncited by 2
  27. 2024STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenariocited by 2
  28. 2024Boosting Few-Pixel Robustness Verification via Covering Verification Designscited by 2
  29. 2024Query-Efficient Hard-Label Black-Box Attack against Vision Transformerscited by 2
  30. 2025GSBAK: top-K Geometric Score-based Black-box Attackcited by 2
  31. 2025CertMask: Certifiable Defense Against Adversarial Patches via Theoretically Optimal Mask Coveragecited by 2
  32. 2021LSDAT: Low-Rank and Sparse Decomposition for Decision-based Adversarial Attackcited by 1
  33. 2022Efficient and Robust Classification for Sparse Attackscited by 1
  34. 2024Sparse and Transferable Universal Singular Vectors Attackcited by 1
  35. 2024RAMP: Boosting Adversarial Robustness Against Multiple lp Perturbations for Universal Robustnesscited by 1
  36. 2025Towards Interpretable Adversarial Examples via Sparse Adversarial Attackcited by 1
  37. 2025Tight Robustness Certification Through the Convex Hull of ℓ0 Attackscited by 1
  38. 2025Power Homotopy for Zeroth-Order Non-Convex Optimizationscited by 1

50 most cited of 65 All 65 (JSON)