mlsanityData to 14 Oct 2026

Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction

arXiv 1911.11616 ↗First posted 22 Nov 2019eess.IV cs.CR cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they remain adversarial even against other models. Although great efforts have been delved into the transferability across models, surprisingly, less attention has been paid to the cross-task transferability, which represents the real-world cybercriminal's situation, where an ensemble of different defense/detection mechanisms need to be evaded all at once. In this paper, we investigate the transferability of adversarial examples across a wide range of real-world computer vision tasks, including image classification, object detection, semantic segmentation, explicit content detection, and text detection. Our proposed attack minimizes the ``dispersion'' of the internal feature map, which overcomes existing attacks' limitation of requiring task-specific loss functions and/or probing a target model. We conduct evaluation on open source detection and segmentation models as well as four different computer vision tasks provided by Google Cloud Vision (GCV) APIs, to show how our approach outperforms existing attacks by degrading performance of multiple CV tasks by a large margin with only modest perturbations linf=16.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 9; 2022: 11; 2023: 7; 2024: 11; 2025: 7; 2026: 2.

47 papers.

Sort:

By area:

  1. 2021Feature Importance-aware Transferable Adversarial Attackscited by 127
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 94
  4. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  5. 2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Modelscited by 68
  6. 2022Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Inputcited by 50
  7. 2024An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Modelscited by 45
  8. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 44
  9. 2022Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domainscited by 42
  10. 2024CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attackscited by 19
  11. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 17
  12. 2022Pre-trained Adversarial Perturbationscited by 16
35 more
  1. 2024As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?cited by 11
  2. 2024VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Modelscited by 10
  3. 2021Black-box Adversarial Attacks in Autonomous Vehicle Technologycited by 9
  4. 2021Fast Gradient Non-sign Methodscited by 9
  5. 2022Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformationcited by 9
  6. 2024Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shiftcited by 9
  7. 2024Prompt-Driven Contrastive Learning for Transferable Adversarial Attackscited by 9
  8. 2025Cross-Modal Transferable Image-to-Video Attack on Video Quality Metricscited by 9
  9. 2024FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attackscited by 8
  10. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  11. 2021Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchycited by 4
  12. 2022General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignmentscited by 4
  13. 2024Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokenscited by 4
  14. 2025AIM: Additional Image Guided Generation of Transferable Adversarial Attackscited by 4
  15. 2021Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?cited by 3
  16. 2021Detect & Reject for Transferability of Black-box Adversarial Attacks Against Network Intrusion Detection Systemscited by 3
  17. 2022Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Surveycited by 3
  18. 2021Adversarial Attack across Datasetscited by 2
  19. 2023Boosting Cross-task Transferability of Adversarial Patches with Visual Relationscited by 2
  20. 2024Adversarial Attacks on Hidden Tasks in Multi-Task Learningcited by 2
  21. 2025Fading the Digital Ink: A Universal Black-Box Attack Framework for 3DGS Watermarking Systemscited by 2
  22. 2022Adversarial samples for deep monocular 6D object pose estimationcited by 1
  23. 2022SSMI: How to Make Objects of Interest Disappear without Accessing Object Detectors?cited by 1
  24. 2024Probing Human Visual Robustness with Neurally-Guided Deep Neural Networkscited by 1
  25. 2024Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformerscited by 1
  26. 2025Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimizationcited by 1
  27. 2025Adversarial Attacks on VQA-NLE: Exposing and Alleviating Inconsistencies in Visual Question Answering Explanationscited by 1
  28. 2021Cross-Modal Transferable Adversarial Attacks from Images to Videoscited by 0
  29. 2022Adversarially robust segmentation models learn perceptually-aligned gradientscited by 0
  30. 2022AdvSmo: Black-box Adversarial Attack by Smoothing Linear Structure of Texturecited by 0
  31. 2023Robust Network Slicing: Multi-Agent Policies, Adversarial Attacks, and Defensive Strategiescited by 0
  32. 2025Revealing Hidden Vulnerabilities in Autoencoders through Gradient Signal Restorationcited by 0
  33. 2025Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Modelscited by 0
  34. 2026Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correctioncited by 0
  35. 2026On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspacescited by 0