mlsanityData to 7 Oct 2026

Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks

arXiv 2303.01978 ↗First posted 26 Jan 2023cs.LGcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose a new method, dubbed One Class Signed Distance Function (OCSDF), to perform One Class Classification (OCC) by provably learning the Signed Distance Function (SDF) to the boundary of the support of any distribution. The distance to the support can be interpreted as a normality score, and its approximation using 1-Lipschitz neural networks provides robustness bounds against l2 adversarial attacks, an under-explored weakness of deep learning-based OCC algorithms. As a result, OCSDF comes with a new metric, certified AUROC, that can be computed at the same cost as any classical AUROC. We show that OCSDF is competitive against concurrent methods on tabular and image data while being way more robust to adversarial attacks, illustrating its theoretical properties. Finally, as exploratory research perspectives, we theoretically and empirically show how OCSDF connects OCC with image generation and implicit neural surface parametrization. Our code is available at https://github.com/Algue-Rythme/OneClassMetricLearning

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 54 of its 92 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

54 of 92 references.

References · 54

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  12. 2019Adversarial Training for Free!cited by 638
38 more
  1. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  2. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  3. 2017Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samplescited by 389
  4. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  5. 2017Nearly-tight VC-dimension and pseudodimension bounds for piecewise linear neural networkscited by 304
  6. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  7. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  8. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  9. 2022ADBench: Anomaly Detection Benchmarkcited by 230
  10. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
  11. 2019PyOD: A Python Toolbox for Scalable Outlier Detectioncited by 221
  12. 2018Sorting out Lipschitz function approximationcited by 211
  13. 2020Classification-Based Anomaly Detection for General Datacited by 210
  14. 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
  15. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 193
  16. 2022(Certified!!) Adversarial Robustness for Free!cited by 130
  17. 2019Orthogonal Convolutional Neural Networkscited by 122
  18. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  19. 2018Adversarially Learned Anomaly Detectioncited by 115
  20. 2021Orthogonalizing Convolutional Layers with the Cayley Transformcited by 105
  21. 2020Exactly Computing the Local Lipschitz Constant of ReLU Networkscited by 102
  22. 2019Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networkscited by 86
  23. 2019Orthogonal Deep Neural Networkscited by 72
  24. 2021Skew Orthogonal Convolutionscited by 67
  25. 2020G2D: Generate to Detect Anomalycited by 42
  26. 2022LOT: Layer-wise Orthogonal Training on Improving ℓ2 Certified Robustnesscited by 32
  27. 2021Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networkscited by 30
  28. 2022GenSDF: Two-Stage Learning of Generalizable Signed Distance Functionscited by 30
  29. 2020Approximating Lipschitz continuous functions with GroupSort neural networkscited by 27
  30. 2020Achieving robustness in classification using optimal transport with hinge regularizationcited by 27
  31. 2020Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failurecited by 27
  32. 2018Multi-chart Generative Surface Modelingcited by 26
  33. 2022Exploring Differential Geometry in Neural Implicitscited by 26
  34. 2021Adversarially Robust One-class Novelty Detectioncited by 24
  35. 2022Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solutioncited by 24
  36. 2021Existence, Stability and Scalability of Orthogonal Convolutional Neural Networkscited by 16
  37. 2022Your Out-of-Distribution Detection Method is Not Robust!cited by 16
  38. 2021Convolutional Normalization: Improving Deep Convolutional Network Robustness and Trainingcited by 15

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 6.

10 papers.

  1. 20241-Lipschitz Neural Distance Fieldscited by 8
  2. 2025PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomaliescited by 8
  3. 2025RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samplescited by 7
  4. 2025Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Modelscited by 7
  5. 2024Adversarially Robust Out-of-Distribution Detection Using Lyapunov-Stabilized Embeddingscited by 6
  6. 2025Killing it with Zero-Shot: Adversarially Robust Novelty Detectioncited by 4
  7. 2025Scanning Trojaned Models Using Out-of-Distribution Samplescited by 3
  8. 2023DP-SGD with weight clippingcited by 1
  9. 2024Solving robust MDPs as a sequence of static RL problemscited by 1
  10. 2025HALO: Robust Out-of-Distribution Detection via Joint Optimisationcited by 0