mlsanityData to 7 Oct 2026

An Intermediate-level Attack Framework on The Basis of Linear Regression

arXiv 2203.10723 ↗First posted 21 Mar 2022cs.CV cs.CR cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct linear mapping from the intermediate-level discrepancies (between adversarial features and benign features) to prediction loss of the adversarial example is established. By delving deep into the core components of such a framework, we show that 1) a variety of linear regression models can all be considered in order to establish the mapping, 2) the magnitude of the finally obtained intermediate-level adversarial discrepancy is correlated with the transferability, 3) further boost of the performance can be achieved by performing multiple runs of the baseline attack with random initialization. In addition, by leveraging these findings, we achieve new state-of-the-arts on transfer-based ℓ_∞ and ℓ2 attacks. Our code is publicly available at https://github.com/qizhangli/ila-plus-plus-lr.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 21 Mar 2022.

Builds on

35 of 49 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  10. 2017Squeeze-and-Excitation Networkscited by 4,763
  11. 2016Wide Residual Networkscited by 3,057
  12. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
23 more
  1. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  2. 2016Adversarial Machine Learning at Scalecited by 934
  3. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  4. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  5. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  6. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  7. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  8. 2017Progressive Neural Architecture Searchcited by 483
  9. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  10. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  11. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  12. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  13. 2019Simple Black-box Adversarial Attackscited by 249
  14. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  15. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  16. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  17. 2021Feature Importance-aware Transferable Adversarial Attackscited by 125
  18. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  19. 2020A Unified Approach to Interpreting and Boosting Adversarial Transferabilitycited by 71
  20. 2019Black-Box Adversarial Attack with Transferable Model-based Embeddingcited by 57
  21. 2019Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attackscited by 35
  22. 2020Yet Another Intermediate-Level Attackcited by 35
  23. 2021A Little Robustness Goes a Long Way: Leveraging Robust Features for Targeted Transfer Attackscited by 33

Built on by

Cited by year

Citing papers per year: 2023: 7; 2024: 2.

9 papers.

  1. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  2. 2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
  3. 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMscited by 17
  4. 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairlycited by 6
  5. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  6. 2023A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarkingcited by 5
  7. 2023LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogatecited by 5
  8. 2024BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Modelscited by 5
  9. 2023Improving Transferability of Adversarial Examples via Bayesian Attackscited by 3