mlsanityData to 7 Oct 2026

Transferable Adversarial Attack based on Integrated Gradients

arXiv 2205.13152 ↗First posted 26 May 2022cs.LG cs.CVcited by 35

Not on the map. Why?

Abstract (arXiv)

The vulnerability of deep neural networks to adversarial examples has drawn tremendous attention from the community. Three approaches, optimizing standard objective functions, exploiting attention maps, and smoothing decision surfaces, are commonly used to craft adversarial examples. By tightly integrating the three approaches, we propose a new and simple algorithm named Transferable Attack based on Integrated Gradients (TAIG) in this paper, which can find highly transferable adversarial examples for black-box attacks. Unlike previous methods using multiple computational terms or combining with other methods, TAIG integrates the three approaches into one single term. Two versions of TAIG that compute their integrated gradients on a straight-line path and a random piecewise linear path are studied. Both versions offer strong transferability and can seamlessly work together with the previous methods. Experimental results demonstrate that TAIG outperforms the state-of-the-art methods. The code will available at https://github.com/yihuang2016/TAIG

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

42 of 54 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  9. 2017Squeeze-and-Excitation Networkscited by 4,763
  10. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  11. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  12. 2016Adversarial examples in the physical worldcited by 1,762
30 more
  1. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  3. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  4. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  5. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  6. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  7. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  8. 2017Progressive Neural Architecture Searchcited by 483
  9. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  10. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  11. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  12. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 352
  13. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  14. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  15. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
  16. 2021Admix: Enhancing the Transferability of Adversarial Attackscited by 155
  17. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  18. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  19. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  20. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  21. 2018ComDefend: An Efficient Image Compression Model to Defend Adversarial Examplescited by 104
  22. 2018Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examplescited by 98
  23. 2018Adversarial Attacks and Defences Competitioncited by 96
  24. 2020Backpropagating Linearly Improves Transferability of Adversarial Examplescited by 79
  25. 2019Black-Box Adversarial Attack with Transferable Model-based Embeddingcited by 57
  26. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  27. 2020Universal Adversarial Attack on Attention and the Resulting Dataset DAmageNetcited by 45
  28. 2020Smoothed Geometry for Robust Attributioncited by 38
  29. 2019Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attackscited by 35
  30. 2019Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagationcited by 29

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 14; 2024: 9; 2025: 4; 2026: 4.

35 papers.

Sort:

By area:

  1. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 43
  2. 2023SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentationcited by 39
  3. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  4. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  5. 2023Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognitioncited by 32
  6. 2023Improving Adversarial Transferability via Intermediate-level Perturbation Decaycited by 29
  7. 2022Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learningcited by 15
  8. 2023Reliable Evaluation of Adversarial Transferabilitycited by 12
  9. 2025MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Modelscited by 11
  10. 2023TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentationcited by 10
  11. 2024Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Pathcited by 10
  12. 2025Towards Model Resistant to Transferable Adversarial Examples via Trigger Activationcited by 10
23 more
  1. 2024Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustnesscited by 8
  2. 2022Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentationcited by 7
  3. 2023Boosting Adversarial Transferability via Fusing Logits of Top-1 Decomposed Featurecited by 6
  4. 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairlycited by 6
  5. 2023LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogatecited by 5
  6. 2024Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Modelscited by 5
  7. 2024LibraGrad: Balancing Gradient Flow for Universally Better Vision Transformer Attributionscited by 5
  8. 2023Generating Adversarial Examples with Better Transferability via Masking Unimportant Parameters of Surrogate Modelcited by 4
  9. 2023Improving Transferability of Adversarial Examples via Bayesian Attackscited by 3
  10. 2022Enhancing Targeted Attack Transferability via Diversified Weight Pruningcited by 2
  11. 2024AdaptGrad: Adaptive Sampling to Reduce Noisecited by 2
  12. 2024Transferable Adversarial Attacks against ASRcited by 2
  13. 2023How to choose your best allies for a transferable attack?cited by 1
  14. 2023Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Methodcited by 1
  15. 2024On the Adversarial Transferability of Generalized "Skip Connections"cited by 1
  16. 2026Transferable Attack against Face Swapping in an Extended Spacecited by 1
  17. 2024Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challengescited by 0
  18. 2024On the Robustness of Distributed Machine Learning against Transfer Attackscited by 0
  19. 2025Differentiable Adversarial Attacks for Marked Temporal Point Processescited by 0
  20. 2025Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiationcited by 0
  21. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0
  22. 2026MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Eliminationcited by 0
  23. 2026IGME: Efficient Chained Method Ensemble for Transferable Semantic Segmentation Attackscited by 0