mlsanityData to 7 Oct 2026

Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning

arXiv 2209.00005 ↗First posted 31 Aug 2022cs.LG cs.CRcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) have achieved excellent performance in various fields. However, DNNs' vulnerability to Adversarial Examples (AE) hinders their deployments to safety-critical applications. This paper presents a novel AE detection framework, named BEYOND, for trustworthy predictions. BEYOND performs the detection by distinguishing the AE's abnormal relation with its augmented versions, i.e. neighbors, from two prospects: representation similarity and label consistency. An off-the-shelf Self-Supervised Learning (SSL) model is used to extract the representation and predict the label for its highly informative representation capacity compared to supervised learning models. For clean samples, their representations and predictions are closely consistent with their neighbors, whereas those of AEs differ greatly. Furthermore, we explain this observation and show that by leveraging this discrepancy BEYOND can effectively detect AEs. We develop a rigorous justification for the effectiveness of BEYOND. Furthermore, as a plug-and-play model, BEYOND can easily cooperate with the Adversarial Trained Classifier (ATC), achieving the state-of-the-art (SOTA) robustness accuracy. Experimental results show that BEYOND outperforms baselines by a large margin, especially under adaptive attacks. Empowered by the robust relation net built on SSL, we found that BEYOND outperforms baselines in terms of both detection ability and speed. Our code will be publicly available.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 31 Aug 2022.

Builds on

43 of 56 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  8. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  9. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 935
  10. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  11. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  12. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
31 more
  1. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  3. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  4. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  5. 2019Adversarial Examples Improve Image Recognitioncited by 283
  6. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  7. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  8. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  9. 2021Improving Robustness using Generated Datacited by 233
  10. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  11. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  12. 2020Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNetscited by 165
  13. 2017The Space of Transferable Adversarial Examplescited by 156
  14. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  15. 2020Adversarial Self-Supervised Contrastive Learningcited by 138
  16. 2021Solo-learn: A Library of Self-supervised Methods for Visual Representation Learningcited by 116
  17. 2020Contrastive Learning with Adversarial Examplescited by 91
  18. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  19. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  20. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
  21. 2021Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Themcited by 46
  22. 2019Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networkscited by 40
  23. 2021Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descentcited by 34
  24. 2018Detection based Defense against Adversarial Examples from the Steganalysis Point of Viewcited by 32
  25. 2021Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domaincited by 29
  26. 2019DLA: Dense-Layer-Analysis for Adversarial Example Detectioncited by 20
  27. 2019Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Searchcited by 19
  28. 2022Demystifying the Adversarial Robustness of Random Transformation Defensescited by 14
  29. 2022What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradictioncited by 10
  30. 2018PeerNets: Exploiting Peer Wisdom Against Adversarial Attackscited by 8
  31. 2020A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networkscited by 7

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 2.

5 papers.

  1. 2023New Adversarial Image Detection Based on Sentiment Analysiscited by 6
  2. 2024Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectorscited by 4
  3. 2025FlowPure: Continuous Normalizing Flows for Adversarial Purificationcited by 2
  4. 2025A Few Large Shifts: Layer-Inconsistency Based Minimal Overhead Adversarial Example Detectioncited by 1
  5. 2023Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejectioncited by 0