mlsanityData to 14 Oct 2026

Yet Another Intermediate-Level Attack

arXiv 2008.08847 ↗First posted 20 Aug 2020cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

The transferability of adversarial examples across deep neural network (DNN) models is the crux of a spectrum of black-box attacks. In this paper, we propose a novel method to enhance the black-box transferability of baseline adversarial examples. By establishing a linear mapping of the intermediate-level discrepancies (between a set of adversarial inputs and their benign counterparts) for predicting the evoked adversarial loss, we aim to take full advantage of the optimization procedure of multi-step baseline attacks. We conducted extensive experiments to verify the effectiveness of our method on CIFAR-100 and ImageNet. Experimental results demonstrate that it outperforms previous state-of-the-arts considerably. Our code is at https://github.com/qizhangli/ila-plus-plus.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 7; 2022: 4; 2023: 9; 2024: 9; 2025: 4; 2026: 2.

35 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021RobustART: Benchmarking Robustness on Architecture Design and Training Techniquescited by 79
  3. 2021On Generating Transferable Targeted Perturbationscited by 65
  4. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  5. 2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
  6. 2022Investigating Top-k White-Box and Transferable Black-box Attackcited by 26
  7. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 23
  8. 2024Transferable Adversarial Attacks on SAM and Its Downstream Modelscited by 21
  9. 2024CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attackscited by 19
  10. 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMscited by 18
  11. 2022Towards Good Practices in Evaluating Transfer Adversarial Attackscited by 15
  12. 2023Fast Adversarial Training with Smooth Convergencecited by 14
23 more
  1. 2021Learning to Learn Transferable Attackcited by 13
  2. 2023StyLess: Boosting the Transferability of Adversarial Examplescited by 11
  3. 2023Attacking Perceptual Similarity Metricscited by 10
  4. 2022An Intermediate-level Attack Framework on The Basis of Linear Regressioncited by 9
  5. 2023GNP Attack: Transferable Adversarial Examples via Gradient Norm Penaltycited by 8
  6. 2024Enhancing targeted transferability via feature space fine-tuningcited by 7
  7. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
  8. 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairlycited by 6
  9. 2024Improving Transferable Targeted Attacks with Feature Tuning Mixupcited by 6
  10. 2024BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Modelscited by 5
  11. 2021Exploring Transferable and Robust Adversarial Perturbation Generation from the Perspective of Network Hierarchycited by 4
  12. 2021Can Targeted Adversarial Examples Transfer When the Source and Target Models Have No Label Space Overlap?cited by 3
  13. 2023Improving Transferability of Adversarial Examples via Bayesian Attackscited by 3
  14. 2025Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimizationcited by 1
  15. 2025NAT: Learning to Attack Neurons for Enhanced Adversarial Transferabilitycited by 1
  16. 2021A Perceptual Distortion Reduction Framework: Towards Generating Adversarial Examples with High Perceptual Quality and Attack Success Ratecited by 0
  17. 2022Gradient Aligned Attacks via a Few Queriescited by 0
  18. 2024AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptationcited by 0
  19. 2024Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferabilitycited by 0
  20. 2025Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approachcited by 0
  21. 2025Improving Black-Box Generative Attacks via Generator Semantic Consistencycited by 0
  22. 2026Feature-Space Smoothing: Certified Robustness of Deep Representationscited by 0
  23. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0