mlsanityData to 7 Oct 2026

Benchmarking Transferable Adversarial Attacks

arXiv 2402.00418 ↗First posted 1 Feb 2024cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

The robustness of deep learning models against adversarial attacks remains a pivotal concern. This study presents, for the first time, an exhaustive review of the transferability aspect of adversarial attacks. It systematically categorizes and critically evaluates various methodologies developed to augment the transferability of adversarial attacks. This study encompasses a spectrum of techniques, including Generative Structure, Semantic Similarity, Gradient Editing, Target Modification, and Ensemble Approach. Concurrently, this paper introduces a benchmark framework textitTAA-Bench, integrating ten leading methodologies for adversarial attack transferability, thereby providing a standardized and systematic platform for comparative analysis across diverse model architectures. Through comprehensive scrutiny, we delineate the efficacy and constraints of each method, shedding light on their underlying operational principles and practical utility. This review endeavors to be a quintessential resource for both scholars and practitioners in the field, charting the complex terrain of adversarial transferability and setting a foundation for future explorations in this vital sector. The associated codebase is accessible at: https://github.com/KxPlaug/TAA-Bench

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 20 of its 25 references that are in the map. First posted on arXiv 1 Feb 2024.

Builds on

20 of 25 references.

References · 20

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Adversarial examples in the physical worldcited by 1,762
  3. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  4. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  5. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  6. 2018Adversarial Attacks and Defences: A Surveycited by 259
  7. 2018Generating Adversarial Examples with Adversarial Networkscited by 256
  8. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  9. 2022Frequency Domain Model Augmentation for Adversarial Attackcited by 128
  10. 2021Feature Importance-aware Transferable Adversarial Attackscited by 125
  11. 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 92
  12. 2020On Success and Simplicity: A Second Look at Transferable Targeted Attackscited by 89
8 more
  1. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  2. 2023Structure Invariant Transformation for better Adversarial Transferabilitycited by 61
  3. 2023Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularizationcited by 42
  4. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  5. 2022Investigating Top-k White-Box and Transferable Black-box Attackcited by 26
  6. 2023DANAA: Towards transferable attacks with double adversarial neuron attributioncited by 7
  7. 2024GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative modelcited by 7
  8. 2023Towards Transferable Adversarial Attacks with Centralized Perturbationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 1.

5 papers.

  1. 2025TabAttackBench: A Benchmark for Adversarial Attacks on Tabular Datacited by 4
  2. 2025Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretabilitycited by 3
  3. 2024Leveraging Information Consistency in Frequency and Spatial Domain for Adversarial Attackscited by 0
  4. 2024Attribution for Enhanced Explanation with Transferable Adversarial eXplorationcited by 0
  5. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0