mlsanityData to 7 Oct 2026

Understanding and Enhancing the Transferability of Adversarial Examples

arXiv 1802.09707 ↗First posted 27 Feb 2018stat.ML cs.CR cs.LGcited by 41

Not on the map. Why?

Abstract (arXiv)

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can textittransfer across models: adversarial examples generated for a specific model will often mislead other unseen models. Consequently the adversary can leverage it to attack deployed systems without any query, which severely hinder the application of deep learning, especially in the areas where security is crucial. In this work, we systematically study how two classes of factors that might influence the transferability of adversarial examples. One is about model-specific factors, including network architecture, model capacity and test accuracy. The other is the local smoothness of loss function for constructing adversarial examples. Based on these understanding, a simple but effective strategy is proposed to enhance transferability. We call it variance-reduced attack, since it utilizes the variance-reduced gradient to generate adversarial example. The effectiveness is confirmed by a variety of experiments on both CIFAR-10 and ImageNet datasets.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 7; 2023: 11; 2024: 4; 2025: 7.

41 papers.

Sort:

By area:

  1. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  2. 2023Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Modelscited by 72
  3. 2024Failures to Find Transferable Image Jailbreaks Between Vision-Language Modelscited by 27
  4. 2021Unrestricted Adversarial Attacks on ImageNet Competitioncited by 23
  5. 2021Boosting the Transferability of Video Adversarial Examples via Temporal Translationcited by 21
  6. 2023A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attackscited by 19
  7. 2021Attack to Fool and Explain Deep Networkscited by 17
  8. 2021Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removalcited by 16
  9. 2021Training Meta-Surrogate Model for Transferable Adversarial Attackcited by 15
  10. 2022Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learningcited by 15
  11. 2025Adversarial Examples Are Not Bugs, They Are Superpositioncited by 13
  12. 2022Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferabilitycited by 12
29 more
  1. 2022Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settingscited by 11
  2. 2021Demystifying the Transferability of Adversarial Attacks in Computer Networkscited by 9
  3. 2022On the Role of Generalization in Transferability of Adversarial Examplescited by 9
  4. 2021What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Spacecited by 8
  5. 2023Adversarial Attack Based on Prediction-Correctioncited by 7
  6. 2025TarPro: Targeted Protection against Malicious Image Editingcited by 7
  7. 2021Who's Afraid of Adversarial Transferability?cited by 6
  8. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  9. 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairlycited by 6
  10. 2021Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropoutcited by 5
  11. 2022Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attackscited by 5
  12. 2023LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogatecited by 5
  13. 2021Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchycited by 4
  14. 2023Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimizationcited by 4
  15. 2021Adversarial Attack across Datasetscited by 2
  16. 2025Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Modelscited by 2
  17. 2022Using adversarial images to improve outcomes of federated learning for non-IID datacited by 1
  18. 2023Towards the Transferable Audio Adversarial Attack via Ensemble Methodscited by 1
  19. 2024Network transferability of adversarial patches in real-time object detectioncited by 1
  20. 2025NAT: Learning to Attack Neurons for Enhanced Adversarial Transferabilitycited by 1
  21. 2025SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack against No-Reference Image Quality Assessment Modelscited by 1
  22. 2025Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearningcited by 1
  23. 2022Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classificationcited by 0
  24. 2023Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attackscited by 0
  25. 2023On the Computational Entanglement of Distant Features in Adversarial Machine Learningcited by 0
  26. 2023Facial Data Minimization: Shallow Model as Your Privacy Filtercited by 0
  27. 2024Properties that allow or prohibit transferability of adversarial attacks among quantized networkscited by 0
  28. 2024Preventing Non-intrusive Load Monitoring Privacy Invasion: A Precise Adversarial Attack Scheme for Networked Smart Meterscited by 0
  29. 2025Adversarial VR: An Open-Source Testbed for Evaluating Adversarial Robustness of VR Cybersickness Detection and Mitigationcited by 0