mlsanityData to 14 Oct 2026

Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality

arXiv 1801.02613 ↗First posted 8 Jan 2018cs.LG cs.CR cs.CVcited by 282

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) have recently been shown to be vulnerable against adversarial examples, which are carefully crafted instances that can mislead DNNs to make errors during prediction. To better understand such attacks, a characterization is needed of the properties of regions (the so-called 'adversarial subspaces') in which adversarial examples lie. We tackle this challenge by characterizing the dimensional properties of adversarial regions, via the use of Local Intrinsic Dimensionality (LID). LID assesses the space-filling capability of the region surrounding a reference example, based on the distance distribution of the example to its neighbors. We first provide explanations about how adversarial perturbation can affect the LID characteristic of adversarial regions, and then show empirically that LID characteristics can facilitate the distinction of adversarial examples generated using state-of-the-art attacks. As a proof-of-concept, we show that a potential application of LID is to distinguish adversarial examples, and the preliminary results show that it can outperform several state-of-the-art detection measures by large margins for five attack strategies considered in this paper across three benchmark datasets. Our analysis of the LID characteristic for adversarial regions not only motivates new directions of effective adversarial defense, but also opens up more challenges for developing new attacks to better understand the vulnerabilities of DNNs.

Key facts. Cited by 282 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 76; 2022: 57; 2023: 49; 2024: 32; 2025: 37; 2026: 31.

282 papers.

Sort:

By area:

  1. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 324
  2. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 193
  3. 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
  4. 2021Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Bettercited by 79
  5. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  6. 2021Exploring Architectural Ingredients of Adversarially Robust Deep Neural Networkscited by 74
  7. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  8. 2023X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detectioncited by 59
  9. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  10. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  11. 2021Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Themcited by 48
  12. 2024Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimensioncited by 45
38 more
  1. 2023Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionalitycited by 44
  2. 2021Consistency Regularization for Adversarial Robustnesscited by 42
  3. 2022Enhancing Adversarial Training with Second-Order Statistics of Weightscited by 42
  4. 2024A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Modelscited by 42
  5. 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
  6. 2021On the Certified Robustness for Ensemble Models and Beyondcited by 40
  7. 2021CausalAdv: Adversarial Robustness through the Lens of Causalitycited by 37
  8. 2021Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descentcited by 35
  9. 2023Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferabilitycited by 32
  10. 2021SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domaincited by 30
  11. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  12. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  13. 2022iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detectioncited by 27
  14. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 25
  15. 2021Towards Defending against Adversarial Examples via Attack-Invariant Featurescited by 25
  16. 2022Intrinsic Dimensionality Estimation within Tight Localities: A Theoretical and Experimental Analysiscited by 22
  17. 2024BadActs: A Universal Backdoor Defense in the Activation Spacecited by 21
  18. 2023Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Scorecited by 20
  19. 2022Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attackscited by 19
  20. 2021Removing Adversarial Noise in Class Activation Feature Spacecited by 18
  21. 2022Adversarial Rademacher Complexity of Deep Neural Networkscited by 18
  22. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  23. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  24. 2021Security and Privacy for Artificial Intelligence: Opportunities and Challengescited by 16
  25. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Surveycited by 16
  26. 2022Self-Ensembling Vision Transformer (SEViT) for Robust Medical Image Classificationcited by 16
  27. 2023CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseencited by 15
  28. 2025AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defensescited by 15
  29. 2021Attack as Defense: Characterizing Adversarial Examples using Robustnesscited by 14
  30. 2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
  31. 2022Gradient-Based Adversarial and Out-of-Distribution Detectioncited by 14
  32. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  33. 2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
  34. 2022Towards Lightweight Black-Box Attacks against Deep Neural Networkscited by 13
  35. 2021Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistencycited by 12
  36. 2022Topology and geometry of data manifold in deep learningcited by 12
  37. 2022Understanding Adversarial Robustness Against On-manifold Adversarial Examplescited by 12
  38. 2021Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddingscited by 11

50 most cited of 282 All 282 (JSON)