mlsanityData to 14 Oct 2026

LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity

arXiv 2207.13129 ↗First posted 26 Jul 2022cs.LG cs.CR cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects multiple weight sets from a few additional training epochs with a constant and high learning rate. LGV exploits two geometric properties that we relate to transferability. First, models that belong to a wider weight optimum are better surrogates. Second, we identify a subspace able to generate an effective surrogate ensemble among this wider optimum. Through extensive experiments, we show that LGV alone outperforms all (combinations of) four established test-time transformations by 1.8 to 59.9 percentage points. Our findings shed new light on the importance of the geometry of the weight space to explain the transferability of adversarial examples.

Key facts. Cited by 39 papers in the map (data through 14 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 26 Jul 2022.

Builds on

27 of 33 references.

References · 27

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Adversarial examples in the physical worldcited by 1,769
  5. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,417
  6. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,352
  7. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,209
  8. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  9. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  10. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 599
  11. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  12. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
15 more
  1. 2018Measuring the Intrinsic Dimension of Objective Landscapescited by 370
  2. 2017Stochastic Gradient Descent as Approximate Bayesian Inferencecited by 300
  3. 2019PyHessian: Neural Networks Through the Lens of the Hessiancited by 292
  4. 2018Gradient Descent Happens in a Tiny Subspacecited by 217
  5. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 210
  6. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 167
  7. 2017The Space of Transferable Adversarial Examplescited by 158
  8. 2019Subspace Inference for Bayesian Deep Learningcited by 95
  9. 2017A General Framework for Adversarial Examples with Objectivescited by 84
  10. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 72
  11. 2018Learning Transferable Adversarial Examples via Ghost Networkscited by 70
  12. 2019Adversarial T-shirt! Evading Person Detectors in A Physical Worldcited by 13
  13. 2021Why flatness does and does not correlate with generalization for deep neural networkscited by 13
  14. 2020Efficient and Transferable Adversarial Examples from Bayesian Neural Networkscited by 10
  15. 2018A Geometric Perspective on the Transferability of Adversarial Directionscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 12; 2024: 15; 2025: 7; 2026: 3.

39 papers.

Sort:

By area:

  1. 2022Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbationcited by 68
  2. 2023A Survey on Transferability of Adversarial Examples across Deep Neural Networkscited by 44
  3. 2023OT-Attack: Enhancing Adversarial Transferability of Vision-Language Models via Optimal Transport Optimizationcited by 37
  4. 2023Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examplescited by 32
  5. 2023Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabilitycited by 32
  6. 2024Transferable Adversarial Attacks on SAM and Its Downstream Modelscited by 21
  7. 2024Improved Generation of Adversarial Examples Against Safety-aligned LLMscited by 18
  8. 2023Reliable Evaluation of Adversarial Transferabilitycited by 13
  9. 2024Bag of Tricks to Boost Adversarial Transferabilitycited by 12
  10. 2023Improving Adversarial Transferability via Model Alignmentcited by 10
  11. 2023Improving the Transferability of Adversarial Examples via Direction Tuningcited by 9
  12. 2024Boosting Adversarial Transferability with Low-Cost Optimization via Maximin Expected Flatnesscited by 7
27 more
  1. 2024Understanding Model Ensemble in Transferable Adversarial Attackcited by 7
  2. 2023Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbationscited by 6
  3. 2023Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairlycited by 6
  4. 2023LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogatecited by 5
  5. 2024Exploring Adversarial Attacks against Latent Diffusion Model from the Perspective of Adversarial Transferabilitycited by 5
  6. 2024Transferable Adversarial Face Attack with Text Controlled Attributecited by 5
  7. 2024The Uncanny Valley: Exploring Adversarial Robustness from a Flatness Perspectivecited by 4
  8. 2024Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentationcited by 4
  9. 2025Exploring Adversarial Transferability between Kolmogorov-arnold Networkscited by 4
  10. 2025Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferabilitycited by 4
  11. 2023Improving Transferability of Adversarial Examples via Bayesian Attackscited by 3
  12. 2022Enhancing Targeted Attack Transferability via Diversified Weight Pruningcited by 2
  13. 2023Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferabilitycited by 2
  14. 2024Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attackcited by 2
  15. 2024Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examplescited by 2
  16. 2024RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defensescited by 2
  17. 2025Concept-based Adversarial Attack: a Probabilistic Perspectivecited by 2
  18. 2024Semantic-Syntactic Discrepancy in Images (SSDI): Learning Meaning and Order of Features from Natural Imagescited by 1
  19. 2024SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledgecited by 1
  20. 2024On Inherent Adversarial Robustness of Active Vision Systemscited by 1
  21. 2025One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMscited by 1
  22. 2025Enabling Heterogeneous Adversarial Transferability via Feature Permutation Attackscited by 0
  23. 2025Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiationcited by 0
  24. 2025On the Trade-Off Between Transparency and Security in Adversarial Machine Learningcited by 0
  25. 2026TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AIcited by 0
  26. 2026Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluationcited by 0
  27. 2026MAPE: Defending Against Transferable Adversarial Attacks Using Multi-Source Adversarial Perturbations Eliminationcited by 0