mlsanityData to 14 Oct 2026

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

arXiv 1807.03888 ↗First posted 10 Jul 2018stat.ML cs.CR cs.LGcited by 1,485

Not on the map. Why?

Cited by 36 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Detecting test samples drawn sufficiently far away from the training distribution statistically or adversarially is a fundamental requirement for deploying a good classifier in many real-world machine learning applications. However, deep neural networks with the softmax classifier are known to produce highly overconfident posterior distributions even for such abnormal samples. In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any pre-trained softmax neural classifier. We obtain the class conditional Gaussian distributions with respect to (low- and upper-level) features of the deep models under Gaussian discriminant analysis, which result in a confidence score based on the Mahalanobis distance. While most prior methods have been evaluated for detecting either out-of-distribution or adversarial samples, but not both, the proposed method achieves the state-of-the-art performances for both cases in our experiments. Moreover, we found that our proposed method is more robust in harsh cases, e.g., when the training dataset has noisy labels or small number of samples. Finally, we show that the proposed method enjoys broader usage by applying it to class-incremental learning: whenever out-of-distribution samples are detected, our classification rule can incorporate new classes well without further training deep models.

Key facts. Cited by 1,485 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 194; 2022: 259; 2023: 273; 2024: 248; 2025: 251; 2026: 259.

1,485 papers.

Sort:

By area:

  1. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  3. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  4. 2023Eliciting Latent Predictions from Transformers with the Tuned Lenscited by 623
  5. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
  7. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  8. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  9. 2021GAN Inversion: A Surveycited by 367
  10. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  11. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  12. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 321
38 more
  1. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
  2. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  3. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  4. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  5. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  6. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  7. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  8. 2022Transformers in Medical Imaging: A Surveycited by 245
  9. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  10. 2022ADBench: Anomaly Detection Benchmarkcited by 232
  11. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  12. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  13. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  14. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  15. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 197
  16. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 179
  17. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  18. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 162
  19. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  20. 2022DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detectioncited by 154
  21. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  22. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  23. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  24. 2021Testing for Outliers with Conformal p-valuescited by 134
  25. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  26. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  27. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 131
  28. 2021SPECTRE: Defending Against Backdoor Attacks Using Robust Statisticscited by 130
  29. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  30. 2023Non-Parametric Outlier Synthesiscited by 129
  31. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  32. 2021Distilling Causal Effect of Data in Class-Incremental Learningcited by 117
  33. 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 116
  34. 2022Multimodal Masked Autoencoders Learn Transferable Representationscited by 109
  35. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  36. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  37. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  38. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107

50 most cited of 1,485 All 1,485 (JSON)